Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)

Overview

Quasi-Dense Tracking

This is the offical implementation of paper Quasi-Dense Similarity Learning for Multiple Object Tracking.

We present a trailer that consists of method illustrations and tracking visualizations. Take a look!

If you have any questions, please go to Discussions.

Abstract

Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions on the images. In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of region proposals on a pair of images for contrastive learning. We can naturally combine this similarity learning with existing detection methods to build Quasi-Dense Tracking (QDTrack) without turning to displacement regression or motion priors. We also find that the resulting distinctive feature space admits a simple nearest neighbor search at the inference time. Despite its simplicity, QDTrack outperforms all existing methods on MOT, BDD100K, Waymo, and TAO tracking benchmarks. It achieves 68.7 MOTA at 20.3 FPS on MOT17 without using external training data. Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets.

Quasi-dense matching

Main results

Without bells and whistles, our method outperforms the states of the art on MOT, BDD100K, Waymo, and TAO benchmarks.

BDD100K test set

mMOTA mIDF1 ID Sw.
35.5 52.3 10790

MOT

Dataset MOTA IDF1 ID Sw. MT ML
MOT16 69.8 67.1 1097 316 150
MOT17 68.7 66.3 3378 957 516

Waymo validation set

Category MOTA IDF1 ID Sw.
Vehicle 55.6 66.2 24309
Pedestrian 50.3 58.4 6347
Cyclist 26.2 45.7 56
All 44.0 56.8 30712

TAO

Split AP50 AP75 AP
val 16.1 5.0 7.0
test 12.4 4.5 5.2

Installation

Please refer to INSTALL.md for installation instructions.

Usages

Please refer to GET_STARTED.md for dataset preparation and running instructions.

We release pretrained models on BDD100K dataset for testing.

More implementations / models on the following benchmarks will be released later:

  • Waymo
  • MOT16 / MOT17 / MOT20
  • TAO

Citation

@InProceedings{qdtrack,
  title = {Quasi-Dense Similarity Learning for Multiple Object Tracking},
  author = {Pang, Jiangmiao and Qiu, Linlu and Li, Xia and Chen, Haofeng and Li, Qi and Darrell, Trevor and Yu, Fisher},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  month = {June},
  year = {2021}
}
Comments
  • TypeError : Resnet : __init__() got an unexpected keyword argument 'init_cfg'

    TypeError : Resnet : __init__() got an unexpected keyword argument 'init_cfg'

    Greetings,

    I am currently using qdtrack in python 3.8, Cuda 11 based environment for RTX 3090 GPU. While training as well as testing, I am getting this error. All required datasets in required locations have been downloaded and maintained. Any help would be appreciated.

    opened by AmanGoyal99 12
  • Inconsistent Results on BDD100K Tracking Validation Set

    Inconsistent Results on BDD100K Tracking Validation Set

    Hi there.

    I ran the pre-trained BDD100K model on the tracking validation set and the resulting MOTA IDF1 scores are lower than what QDTrack claim: MOTA: 54.5, IDF1: 66.7 vs your MOTA: 63.5, IDF1 71.5.

    Kindly verify if this is the case for you or if there are any missing settings.

    I followed the instructions and ran this command: sh ./tools/dist_test.sh ./configs/bdd100k/qdtrack-frcnn_r50_fpn_12e_bdd100k.py ./ckpts/mmdet/qdtrack_frcnn_r50_fpn_12e_bdd100k_13328aed.pth 2 --out exp.pkl --eval track

    opened by taheranjary 8
  • Evaluation results on TAO-val

    Evaluation results on TAO-val

    Hello,

    When I train the model with your code for TAO (i.e., pretrain on LVIS and finetune on TAO-train), I get the following final results on TAO-val. which are lower than the scores reported in the original paper.

    |mAP0.5 | mAP0.75 | mAP[0.5:0.95] | |---------|---------|---------| |13.8 | 5.5 | 6.5 | | 16.1 | 5.0 | 7.0 |

    • above : reproduced // below : original

    Are there any issues that I have to consider for getting the original score?

    Thanks,

    opened by shwoo93 8
  • Training loss/Acc diagram

    Training loss/Acc diagram

    Thanks for the great work!

    I am trying to retrain QDTrack on BDD100k, however, it is converging really slowly (at least for the first epochs). Therefore I wanted to ask, whether it is possible to share your diagrams on training loss and acc?

    Thanks in advance!

    opened by LisaBernhardt 7
  • Unclear which links to pick from BDD website for dataset prep

    Unclear which links to pick from BDD website for dataset prep

    The Readme indicates Detection and Tracking sets, but the site shows 11 options, including: Images, MOT 2020 Labels, MOT 2020 Data, Detection 2020 Labels.

    Also, clicking MOT 2020 Data shows many different options. Should they all be downloaded?

    opened by diesendruck 7
  • about train

    about train

    when I train the net,Epoch 1 ,200/171305 ,the result as follow: lr: 7.992e-03,loss_rpn_cls: nan, loss_rpn_bbox: nan, loss_cls: nan, acc: 81.8194, loss_bbox: nan, loss_track: nan, loss_track_aux: nan, loss: nan why?

    opened by ningqing123 6
  • Is customization of backbone possible as mentioned in the mmdet library ?

    Is customization of backbone possible as mentioned in the mmdet library ?

    Kindly let me know if customization of backbone as mentioned in mmdet library could be used with qdtrack as well ?

    LInk : https://github.com/open-mmlab/mmdetection/blob/master/docs/tutorials/customize_models.md#add-a-new-backbone

    opened by AmanGoyal99 5
  • Your BDD100K instructions are unclear

    Your BDD100K instructions are unclear

    This is what you are saying:

    
    On the official download page, the required data and annotations are
    
    detection set images: Images
    detection set annotations: Detection 2020 Labels
    tracking set images: MOT 2020 Data
    tracking set annotations: MOT 2020 Labels
    

    But there is no Images or MOT 2020 Data on the official website for BDD

    opened by ghost 5
  • I'm confusing with the meaning of auxiliary loss

    I'm confusing with the meaning of auxiliary loss

    Hi , thanks for your great work. According to the paper, There is an auliliary loss, I do not really understand the intuition of this loss. 螢幕擷取畫面 (9)

    Can you give me some more explanation of this loss? Thanks.

    opened by hcv1027 4
  • RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

    RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

    Thank you for your paper and this repo! I would like to test your pretrained model on the BDD100k dataset. Therefore I followed the instructions (https://github.com/SysCV/qdtrack/blob/master/docs/GET_STARTED.md) - downloaded BDD100k, converted annotations as described and stored everything as your folder structure suggests.

    I used 'single-gpu testing' in the chapter 'Test a Model' and executed the following command in the terminal: python tools/test.py ${QDTrack}/configs/qdtrack-frcnn_r50_fpn_12e_bdd100k.py ${QDTrack}/pretrained_models/qdtrack-frcnn_r50_fpn_12e_bdd100k-13328aed.pth --out testrun_01.pkl --eval track --show-dir ${QDTrack}/data/results

    ${QDTrack} = indicates the path on my machine to qdtrack

    I get the following error: image

    Could you please help me solving this issue. Thanks a lot!

    opened by LisaBernhardt 4
  • about MOT17: loss_track degrades to zero after 50 iterations

    about MOT17: loss_track degrades to zero after 50 iterations

    Thanks for your great work! I'm now trying to run qdtrack on MOT17. I find the detection part went well during training and reached a reasonable mAP score. But, the loss of the quasi-dense embedding part degraded fastly to zero within 100 iterations, and obtained very low MOTA, MOTP, IDF1, etc., after training. Note that I modified nothing except the code related to dataset, which I've checked carefully thus I believe is not the reason. Should I modify the settings of quasi-dense embedding head to make it work? Do you have any suggestions? Thank you very much!

    opened by wswdx 4
  • detector freeze problem

    detector freeze problem

    Hi.

    I'm going to freeze the parameters of detector as you say(https://github.com/SysCV/qdtrack/issues/126).

    In qdtrack/models/mot/qdtrack.py, I tried to freeze the detector using freeze_detector(freeze_detector = True). But, when freeze_detector = True, self.detector, I got this error.

    Traceback (most recent call last): File "tools/train.py", line 169, in main() File "tools/train.py", line 140, in main test_cfg=cfg.get('test_cfg')) File "/workspace/qdtrack/qdtrack/models/builder.py", line 15, in build_model return build(cfg, MODELS, dict(train_cfg=train_cfg, test_cfg=test_cfg)) File "/workspace/mmcv/mmcv/cnn/builder.py", line 27, in build_model_from_cfg return build_from_cfg(cfg, registry, default_args) File "/workspace/mmcv/mmcv/utils/registry.py", line 72, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') AttributeError: QDTrack: 'QDTrack' object has no attribute 'backbone'

    image

    Here is the config file I used. image

    I think, image be caused by self.detector.

    How can I put the backbone and neck, rpn_head, roi_head.bbox_head of the detector config file(/configs/base/faster_rcnn_r50_fpn.py) in self.detector?

    Thank you.

    opened by YOOHYOJEONG 1
  • Can I train only tracker?

    Can I train only tracker?

    Hi.

    I trained the detector using mmcv. And, I want to use the detector checkpoint trained using mmcv for the detector of qdtrack without any additional detector learning. In this case, Can I train only tracker of qdtrack?

    If I enter trained checkpoint using mmcv in init_cfg=dict(checkpoint='') in detecotr, is it the same as training only the tracker I mentioned?

    Thank you.

    opened by YOOHYOJEONG 2
  • The model and loaded state dict do not match exactly

    The model and loaded state dict do not match exactly

    Hi,

    Thanks for open-sourcing the code of your great work! Looks like there are some bugs when running the current tools/inference.py.

    When using the configs/bdd100k/qdtrack-frcnn_r50_fpn_12e_bdd100k.py as config and qdtrack-frcnn_r50_fpn_12e_bdd100k-13328aed.pth as the checkpoint (from the google drive link provided in the README file), the model and loaded state dict do not match exactly. Looks like you updated the name of layers but didn't update the definition of the pre-trained model. Manually changing the layer names in the .pth file will work.

    The model and loaded state dict do not match exactly
    
    unexpected key in source state_dict: backbone.conv1.weight, backbone.bn1.weight, backbone.bn1.bias, backbone.bn1.running_mean, backbone.bn1.running_var, backbone.bn1.num_batches_tracked, backbone.layer1.0.conv1.weight, backbone.layer1.0.bn1.weight, backbone.layer1.0.bn1.bias, backbone.layer1.0.bn1.running_mean, backbone.layer1.0.bn1.running_var, backbone.layer1.0.bn1.num_batches_tracked, backbone.layer1.0.conv2.weight, backbone.layer1.0.bn2.weight, backbone.layer1.0.bn2.bias, backbone.layer1.0.bn2.running_mean, backbone.layer1.0.bn2.running_var, backbone.layer1.0.bn2.num_batches_tracked, backbone.layer1.0.conv3.weight, backbone.layer1.0.bn3.weight, backbone.layer1.0.bn3.bias, backbone.layer1.0.bn3.running_mean, backbone.layer1.0.bn3.running_var, backbone.layer1.0.bn3.num_batches_tracked, backbone.layer1.0.downsample.0.weight, backbone.layer1.0.downsample.1.weight, backbone.layer1.0.downsample.1.bias, backbone.layer1.0.downsample.1.running_mean, backbone.layer1.0.downsample.1.running_var, backbone.layer1.0.downsample.1.num_batches_tracked, backbone.layer1.1.conv1.weight, backbone.layer1.1.bn1.weight, backbone.layer1.1.bn1.bias, backbone.layer1.1.bn1.running_mean, backbone.layer1.1.bn1.running_var, backbone.layer1.1.bn1.num_batches_tracked, backbone.layer1.1.conv2.weight, backbone.layer1.1.bn2.weight, backbone.layer1.1.bn2.bias, backbone.layer1.1.bn2.running_mean, backbone.layer1.1.bn2.running_var, backbone.layer1.1.bn2.num_batches_tracked, backbone.layer1.1.conv3.weight, backbone.layer1.1.bn3.weight, backbone.layer1.1.bn3.bias, backbone.layer1.1.bn3.running_mean, backbone.layer1.1.bn3.running_var, backbone.layer1.1.bn3.num_batches_tracked, backbone.layer1.2.conv1.weight, backbone.layer1.2.bn1.weight, backbone.layer1.2.bn1.bias, backbone.layer1.2.bn1.running_mean, backbone.layer1.2.bn1.running_var, backbone.layer1.2.bn1.num_batches_tracked, backbone.layer1.2.conv2.weight, backbone.layer1.2.bn2.weight, backbone.layer1.2.bn2.bias, backbone.layer1.2.bn2.running_mean, backbone.layer1.2.bn2.running_var, backbone.layer1.2.bn2.num_batches_tracked, backbone.layer1.2.conv3.weight, backbone.layer1.2.bn3.weight, backbone.layer1.2.bn3.bias, backbone.layer1.2.bn3.running_mean, backbone.layer1.2.bn3.running_var, backbone.layer1.2.bn3.num_batches_tracked, backbone.layer2.0.conv1.weight, backbone.layer2.0.bn1.weight, backbone.layer2.0.bn1.bias, backbone.layer2.0.bn1.running_mean, backbone.layer2.0.bn1.running_var, backbone.layer2.0.bn1.num_batches_tracked, backbone.layer2.0.conv2.weight, backbone.layer2.0.bn2.weight, backbone.layer2.0.bn2.bias, backbone.layer2.0.bn2.running_mean, backbone.layer2.0.bn2.running_var, backbone.layer2.0.bn2.num_batches_tracked, backbone.layer2.0.conv3.weight, backbone.layer2.0.bn3.weight, backbone.layer2.0.bn3.bias, backbone.layer2.0.bn3.running_mean, backbone.layer2.0.bn3.running_var, backbone.layer2.0.bn3.num_batches_tracked, backbone.layer2.0.downsample.0.weight, backbone.layer2.0.downsample.1.weight, backbone.layer2.0.downsample.1.bias, backbone.layer2.0.downsample.1.running_mean, backbone.layer2.0.downsample.1.running_var, backbone.layer2.0.downsample.1.num_batches_tracked, backbone.layer2.1.conv1.weight, backbone.layer2.1.bn1.weight, backbone.layer2.1.bn1.bias, backbone.layer2.1.bn1.running_mean, backbone.layer2.1.bn1.running_var, backbone.layer2.1.bn1.num_batches_tracked, backbone.layer2.1.conv2.weight, backbone.layer2.1.bn2.weight, backbone.layer2.1.bn2.bias, backbone.layer2.1.bn2.running_mean, backbone.layer2.1.bn2.running_var, backbone.layer2.1.bn2.num_batches_tracked, backbone.layer2.1.conv3.weight, backbone.layer2.1.bn3.weight, backbone.layer2.1.bn3.bias, backbone.layer2.1.bn3.running_mean, backbone.layer2.1.bn3.running_var, backbone.layer2.1.bn3.num_batches_tracked, backbone.layer2.2.conv1.weight, backbone.layer2.2.bn1.weight, backbone.layer2.2.bn1.bias, backbone.layer2.2.bn1.running_mean, backbone.layer2.2.bn1.running_var, backbone.layer2.2.bn1.num_batches_tracked, backbone.layer2.2.conv2.weight, backbone.layer2.2.bn2.weight, backbone.layer2.2.bn2.bias, backbone.layer2.2.bn2.running_mean, backbone.layer2.2.bn2.running_var, backbone.layer2.2.bn2.num_batches_tracked, backbone.layer2.2.conv3.weight, backbone.layer2.2.bn3.weight, backbone.layer2.2.bn3.bias, backbone.layer2.2.bn3.running_mean, backbone.layer2.2.bn3.running_var, backbone.layer2.2.bn3.num_batches_tracked, backbone.layer2.3.conv1.weight, backbone.layer2.3.bn1.weight, backbone.layer2.3.bn1.bias, backbone.layer2.3.bn1.running_mean, backbone.layer2.3.bn1.running_var, backbone.layer2.3.bn1.num_batches_tracked, backbone.layer2.3.conv2.weight, backbone.layer2.3.bn2.weight, backbone.layer2.3.bn2.bias, backbone.layer2.3.bn2.running_mean, backbone.layer2.3.bn2.running_var, backbone.layer2.3.bn2.num_batches_tracked, backbone.layer2.3.conv3.weight, backbone.layer2.3.bn3.weight, backbone.layer2.3.bn3.bias, backbone.layer2.3.bn3.running_mean, backbone.layer2.3.bn3.running_var, backbone.layer2.3.bn3.num_batches_tracked, backbone.layer3.0.conv1.weight, backbone.layer3.0.bn1.weight, backbone.layer3.0.bn1.bias, backbone.layer3.0.bn1.running_mean, backbone.layer3.0.bn1.running_var, backbone.layer3.0.bn1.num_batches_tracked, backbone.layer3.0.conv2.weight, backbone.layer3.0.bn2.weight, backbone.layer3.0.bn2.bias, backbone.layer3.0.bn2.running_mean, backbone.layer3.0.bn2.running_var, backbone.layer3.0.bn2.num_batches_tracked, backbone.layer3.0.conv3.weight, backbone.layer3.0.bn3.weight, backbone.layer3.0.bn3.bias, backbone.layer3.0.bn3.running_mean, backbone.layer3.0.bn3.running_var, backbone.layer3.0.bn3.num_batches_tracked, backbone.layer3.0.downsample.0.weight, backbone.layer3.0.downsample.1.weight, backbone.layer3.0.downsample.1.bias, backbone.layer3.0.downsample.1.running_mean, backbone.layer3.0.downsample.1.running_var, backbone.layer3.0.downsample.1.num_batches_tracked, backbone.layer3.1.conv1.weight, backbone.layer3.1.bn1.weight, backbone.layer3.1.bn1.bias, backbone.layer3.1.bn1.running_mean, backbone.layer3.1.bn1.running_var, backbone.layer3.1.bn1.num_batches_tracked, backbone.layer3.1.conv2.weight, backbone.layer3.1.bn2.weight, backbone.layer3.1.bn2.bias, backbone.layer3.1.bn2.running_mean, backbone.layer3.1.bn2.running_var, backbone.layer3.1.bn2.num_batches_tracked, backbone.layer3.1.conv3.weight, backbone.layer3.1.bn3.weight, backbone.layer3.1.bn3.bias, backbone.layer3.1.bn3.running_mean, backbone.layer3.1.bn3.running_var, backbone.layer3.1.bn3.num_batches_tracked, backbone.layer3.2.conv1.weight, backbone.layer3.2.bn1.weight, backbone.layer3.2.bn1.bias, backbone.layer3.2.bn1.running_mean, backbone.layer3.2.bn1.running_var, backbone.layer3.2.bn1.num_batches_tracked, backbone.layer3.2.conv2.weight, backbone.layer3.2.bn2.weight, backbone.layer3.2.bn2.bias, backbone.layer3.2.bn2.running_mean, backbone.layer3.2.bn2.running_var, backbone.layer3.2.bn2.num_batches_tracked, backbone.layer3.2.conv3.weight, backbone.layer3.2.bn3.weight, backbone.layer3.2.bn3.bias, backbone.layer3.2.bn3.running_mean, backbone.layer3.2.bn3.running_var, backbone.layer3.2.bn3.num_batches_tracked, backbone.layer3.3.conv1.weight, backbone.layer3.3.bn1.weight, backbone.layer3.3.bn1.bias, backbone.layer3.3.bn1.running_mean, backbone.layer3.3.bn1.running_var, backbone.layer3.3.bn1.num_batches_tracked, backbone.layer3.3.conv2.weight, backbone.layer3.3.bn2.weight, backbone.layer3.3.bn2.bias, backbone.layer3.3.bn2.running_mean, backbone.layer3.3.bn2.running_var, backbone.layer3.3.bn2.num_batches_tracked, backbone.layer3.3.conv3.weight, backbone.layer3.3.bn3.weight, backbone.layer3.3.bn3.bias, backbone.layer3.3.bn3.running_mean, backbone.layer3.3.bn3.running_var, backbone.layer3.3.bn3.num_batches_tracked, backbone.layer3.4.conv1.weight, backbone.layer3.4.bn1.weight, backbone.layer3.4.bn1.bias, backbone.layer3.4.bn1.running_mean, backbone.layer3.4.bn1.running_var, backbone.layer3.4.bn1.num_batches_tracked, backbone.layer3.4.conv2.weight, backbone.layer3.4.bn2.weight, backbone.layer3.4.bn2.bias, backbone.layer3.4.bn2.running_mean, backbone.layer3.4.bn2.running_var, backbone.layer3.4.bn2.num_batches_tracked, backbone.layer3.4.conv3.weight, backbone.layer3.4.bn3.weight, backbone.layer3.4.bn3.bias, backbone.layer3.4.bn3.running_mean, backbone.layer3.4.bn3.running_var, backbone.layer3.4.bn3.num_batches_tracked, backbone.layer3.5.conv1.weight, backbone.layer3.5.bn1.weight, backbone.layer3.5.bn1.bias, backbone.layer3.5.bn1.running_mean, backbone.layer3.5.bn1.running_var, backbone.layer3.5.bn1.num_batches_tracked, backbone.layer3.5.conv2.weight, backbone.layer3.5.bn2.weight, backbone.layer3.5.bn2.bias, backbone.layer3.5.bn2.running_mean, backbone.layer3.5.bn2.running_var, backbone.layer3.5.bn2.num_batches_tracked, backbone.layer3.5.conv3.weight, backbone.layer3.5.bn3.weight, backbone.layer3.5.bn3.bias, backbone.layer3.5.bn3.running_mean, backbone.layer3.5.bn3.running_var, backbone.layer3.5.bn3.num_batches_tracked, backbone.layer4.0.conv1.weight, backbone.layer4.0.bn1.weight, backbone.layer4.0.bn1.bias, backbone.layer4.0.bn1.running_mean, backbone.layer4.0.bn1.running_var, backbone.layer4.0.bn1.num_batches_tracked, backbone.layer4.0.conv2.weight, backbone.layer4.0.bn2.weight, backbone.layer4.0.bn2.bias, backbone.layer4.0.bn2.running_mean, backbone.layer4.0.bn2.running_var, backbone.layer4.0.bn2.num_batches_tracked, backbone.layer4.0.conv3.weight, backbone.layer4.0.bn3.weight, backbone.layer4.0.bn3.bias, backbone.layer4.0.bn3.running_mean, backbone.layer4.0.bn3.running_var, backbone.layer4.0.bn3.num_batches_tracked, backbone.layer4.0.downsample.0.weight, backbone.layer4.0.downsample.1.weight, backbone.layer4.0.downsample.1.bias, backbone.layer4.0.downsample.1.running_mean, backbone.layer4.0.downsample.1.running_var, backbone.layer4.0.downsample.1.num_batches_tracked, backbone.layer4.1.conv1.weight, backbone.layer4.1.bn1.weight, backbone.layer4.1.bn1.bias, backbone.layer4.1.bn1.running_mean, backbone.layer4.1.bn1.running_var, backbone.layer4.1.bn1.num_batches_tracked, backbone.layer4.1.conv2.weight, backbone.layer4.1.bn2.weight, backbone.layer4.1.bn2.bias, backbone.layer4.1.bn2.running_mean, backbone.layer4.1.bn2.running_var, backbone.layer4.1.bn2.num_batches_tracked, backbone.layer4.1.conv3.weight, backbone.layer4.1.bn3.weight, backbone.layer4.1.bn3.bias, backbone.layer4.1.bn3.running_mean, backbone.layer4.1.bn3.running_var, backbone.layer4.1.bn3.num_batches_tracked, backbone.layer4.2.conv1.weight, backbone.layer4.2.bn1.weight, backbone.layer4.2.bn1.bias, backbone.layer4.2.bn1.running_mean, backbone.layer4.2.bn1.running_var, backbone.layer4.2.bn1.num_batches_tracked, backbone.layer4.2.conv2.weight, backbone.layer4.2.bn2.weight, backbone.layer4.2.bn2.bias, backbone.layer4.2.bn2.running_mean, backbone.layer4.2.bn2.running_var, backbone.layer4.2.bn2.num_batches_tracked, backbone.layer4.2.conv3.weight, backbone.layer4.2.bn3.weight, backbone.layer4.2.bn3.bias, backbone.layer4.2.bn3.running_mean, backbone.layer4.2.bn3.running_var, backbone.layer4.2.bn3.num_batches_tracked, neck.lateral_convs.0.conv.weight, neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.weight, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.weight, neck.lateral_convs.2.conv.bias, neck.lateral_convs.3.conv.weight, neck.lateral_convs.3.conv.bias, neck.fpn_convs.0.conv.weight, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.weight, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.weight, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.weight, neck.fpn_convs.3.conv.bias, rpn_head.rpn_conv.weight, rpn_head.rpn_conv.bias, rpn_head.rpn_cls.weight, rpn_head.rpn_cls.bias, rpn_head.rpn_reg.weight, rpn_head.rpn_reg.bias, roi_head.bbox_head.fc_cls.weight, roi_head.bbox_head.fc_cls.bias, roi_head.bbox_head.fc_reg.weight, roi_head.bbox_head.fc_reg.bias, roi_head.bbox_head.shared_fcs.0.weight, roi_head.bbox_head.shared_fcs.0.bias, roi_head.bbox_head.shared_fcs.1.weight, roi_head.bbox_head.shared_fcs.1.bias, roi_head.track_head.convs.0.conv.weight, roi_head.track_head.convs.0.gn.weight, roi_head.track_head.convs.0.gn.bias, roi_head.track_head.convs.1.conv.weight, roi_head.track_head.convs.1.gn.weight, roi_head.track_head.convs.1.gn.bias, roi_head.track_head.convs.2.conv.weight, roi_head.track_head.convs.2.gn.weight, roi_head.track_head.convs.2.gn.bias, roi_head.track_head.convs.3.conv.weight, roi_head.track_head.convs.3.gn.weight, roi_head.track_head.convs.3.gn.bias, roi_head.track_head.fcs.0.weight, roi_head.track_head.fcs.0.bias, roi_head.track_head.fc_embed.weight, roi_head.track_head.fc_embed.bias
    
    missing keys in source state_dict: detector.backbone.conv1.weight, detector.backbone.bn1.weight, detector.backbone.bn1.bias, detector.backbone.bn1.running_mean, detector.backbone.bn1.running_var, detector.backbone.layer1.0.conv1.weight, detector.backbone.layer1.0.bn1.weight, detector.backbone.layer1.0.bn1.bias, detector.backbone.layer1.0.bn1.running_mean, detector.backbone.layer1.0.bn1.running_var, detector.backbone.layer1.0.conv2.weight, detector.backbone.layer1.0.bn2.weight, detector.backbone.layer1.0.bn2.bias, detector.backbone.layer1.0.bn2.running_mean, detector.backbone.layer1.0.bn2.running_var, detector.backbone.layer1.0.conv3.weight, detector.backbone.layer1.0.bn3.weight, detector.backbone.layer1.0.bn3.bias, detector.backbone.layer1.0.bn3.running_mean, detector.backbone.layer1.0.bn3.running_var, detector.backbone.layer1.0.downsample.0.weight, detector.backbone.layer1.0.downsample.1.weight, detector.backbone.layer1.0.downsample.1.bias, detector.backbone.layer1.0.downsample.1.running_mean, detector.backbone.layer1.0.downsample.1.running_var, detector.backbone.layer1.1.conv1.weight, detector.backbone.layer1.1.bn1.weight, detector.backbone.layer1.1.bn1.bias, detector.backbone.layer1.1.bn1.running_mean, detector.backbone.layer1.1.bn1.running_var, detector.backbone.layer1.1.conv2.weight, detector.backbone.layer1.1.bn2.weight, detector.backbone.layer1.1.bn2.bias, detector.backbone.layer1.1.bn2.running_mean, detector.backbone.layer1.1.bn2.running_var, detector.backbone.layer1.1.conv3.weight, detector.backbone.layer1.1.bn3.weight, detector.backbone.layer1.1.bn3.bias, detector.backbone.layer1.1.bn3.running_mean, detector.backbone.layer1.1.bn3.running_var, detector.backbone.layer1.2.conv1.weight, detector.backbone.layer1.2.bn1.weight, detector.backbone.layer1.2.bn1.bias, detector.backbone.layer1.2.bn1.running_mean, detector.backbone.layer1.2.bn1.running_var, detector.backbone.layer1.2.conv2.weight, detector.backbone.layer1.2.bn2.weight, detector.backbone.layer1.2.bn2.bias, detector.backbone.layer1.2.bn2.running_mean, detector.backbone.layer1.2.bn2.running_var, detector.backbone.layer1.2.conv3.weight, detector.backbone.layer1.2.bn3.weight, detector.backbone.layer1.2.bn3.bias, detector.backbone.layer1.2.bn3.running_mean, detector.backbone.layer1.2.bn3.running_var, detector.backbone.layer2.0.conv1.weight, detector.backbone.layer2.0.bn1.weight, detector.backbone.layer2.0.bn1.bias, detector.backbone.layer2.0.bn1.running_mean, detector.backbone.layer2.0.bn1.running_var, detector.backbone.layer2.0.conv2.weight, detector.backbone.layer2.0.bn2.weight, detector.backbone.layer2.0.bn2.bias, detector.backbone.layer2.0.bn2.running_mean, detector.backbone.layer2.0.bn2.running_var, detector.backbone.layer2.0.conv3.weight, detector.backbone.layer2.0.bn3.weight, detector.backbone.layer2.0.bn3.bias, detector.backbone.layer2.0.bn3.running_mean, detector.backbone.layer2.0.bn3.running_var, detector.backbone.layer2.0.downsample.0.weight, detector.backbone.layer2.0.downsample.1.weight, detector.backbone.layer2.0.downsample.1.bias, detector.backbone.layer2.0.downsample.1.running_mean, detector.backbone.layer2.0.downsample.1.running_var, detector.backbone.layer2.1.conv1.weight, detector.backbone.layer2.1.bn1.weight, detector.backbone.layer2.1.bn1.bias, detector.backbone.layer2.1.bn1.running_mean, detector.backbone.layer2.1.bn1.running_var, detector.backbone.layer2.1.conv2.weight, detector.backbone.layer2.1.bn2.weight, detector.backbone.layer2.1.bn2.bias, detector.backbone.layer2.1.bn2.running_mean, detector.backbone.layer2.1.bn2.running_var, detector.backbone.layer2.1.conv3.weight, detector.backbone.layer2.1.bn3.weight, detector.backbone.layer2.1.bn3.bias, detector.backbone.layer2.1.bn3.running_mean, detector.backbone.layer2.1.bn3.running_var, detector.backbone.layer2.2.conv1.weight, detector.backbone.layer2.2.bn1.weight, detector.backbone.layer2.2.bn1.bias, detector.backbone.layer2.2.bn1.running_mean, detector.backbone.layer2.2.bn1.running_var, detector.backbone.layer2.2.conv2.weight, detector.backbone.layer2.2.bn2.weight, detector.backbone.layer2.2.bn2.bias, detector.backbone.layer2.2.bn2.running_mean, detector.backbone.layer2.2.bn2.running_var, detector.backbone.layer2.2.conv3.weight, detector.backbone.layer2.2.bn3.weight, detector.backbone.layer2.2.bn3.bias, detector.backbone.layer2.2.bn3.running_mean, detector.backbone.layer2.2.bn3.running_var, detector.backbone.layer2.3.conv1.weight, detector.backbone.layer2.3.bn1.weight, detector.backbone.layer2.3.bn1.bias, detector.backbone.layer2.3.bn1.running_mean, detector.backbone.layer2.3.bn1.running_var, detector.backbone.layer2.3.conv2.weight, detector.backbone.layer2.3.bn2.weight, detector.backbone.layer2.3.bn2.bias, detector.backbone.layer2.3.bn2.running_mean, detector.backbone.layer2.3.bn2.running_var, detector.backbone.layer2.3.conv3.weight, detector.backbone.layer2.3.bn3.weight, detector.backbone.layer2.3.bn3.bias, detector.backbone.layer2.3.bn3.running_mean, detector.backbone.layer2.3.bn3.running_var, detector.backbone.layer3.0.conv1.weight, detector.backbone.layer3.0.bn1.weight, detector.backbone.layer3.0.bn1.bias, detector.backbone.layer3.0.bn1.running_mean, detector.backbone.layer3.0.bn1.running_var, detector.backbone.layer3.0.conv2.weight, detector.backbone.layer3.0.bn2.weight, detector.backbone.layer3.0.bn2.bias, detector.backbone.layer3.0.bn2.running_mean, detector.backbone.layer3.0.bn2.running_var, detector.backbone.layer3.0.conv3.weight, detector.backbone.layer3.0.bn3.weight, detector.backbone.layer3.0.bn3.bias, detector.backbone.layer3.0.bn3.running_mean, detector.backbone.layer3.0.bn3.running_var, detector.backbone.layer3.0.downsample.0.weight, detector.backbone.layer3.0.downsample.1.weight, detector.backbone.layer3.0.downsample.1.bias, detector.backbone.layer3.0.downsample.1.running_mean, detector.backbone.layer3.0.downsample.1.running_var, detector.backbone.layer3.1.conv1.weight, detector.backbone.layer3.1.bn1.weight, detector.backbone.layer3.1.bn1.bias, detector.backbone.layer3.1.bn1.running_mean, detector.backbone.layer3.1.bn1.running_var, detector.backbone.layer3.1.conv2.weight, detector.backbone.layer3.1.bn2.weight, detector.backbone.layer3.1.bn2.bias, detector.backbone.layer3.1.bn2.running_mean, detector.backbone.layer3.1.bn2.running_var, detector.backbone.layer3.1.conv3.weight, detector.backbone.layer3.1.bn3.weight, detector.backbone.layer3.1.bn3.bias, detector.backbone.layer3.1.bn3.running_mean, detector.backbone.layer3.1.bn3.running_var, detector.backbone.layer3.2.conv1.weight, detector.backbone.layer3.2.bn1.weight, detector.backbone.layer3.2.bn1.bias, detector.backbone.layer3.2.bn1.running_mean, detector.backbone.layer3.2.bn1.running_var, detector.backbone.layer3.2.conv2.weight, detector.backbone.layer3.2.bn2.weight, detector.backbone.layer3.2.bn2.bias, detector.backbone.layer3.2.bn2.running_mean, detector.backbone.layer3.2.bn2.running_var, detector.backbone.layer3.2.conv3.weight, detector.backbone.layer3.2.bn3.weight, detector.backbone.layer3.2.bn3.bias, detector.backbone.layer3.2.bn3.running_mean, detector.backbone.layer3.2.bn3.running_var, detector.backbone.layer3.3.conv1.weight, detector.backbone.layer3.3.bn1.weight, detector.backbone.layer3.3.bn1.bias, detector.backbone.layer3.3.bn1.running_mean, detector.backbone.layer3.3.bn1.running_var, detector.backbone.layer3.3.conv2.weight, detector.backbone.layer3.3.bn2.weight, detector.backbone.layer3.3.bn2.bias, detector.backbone.layer3.3.bn2.running_mean, detector.backbone.layer3.3.bn2.running_var, detector.backbone.layer3.3.conv3.weight, detector.backbone.layer3.3.bn3.weight, detector.backbone.layer3.3.bn3.bias, detector.backbone.layer3.3.bn3.running_mean, detector.backbone.layer3.3.bn3.running_var, detector.backbone.layer3.4.conv1.weight, detector.backbone.layer3.4.bn1.weight, detector.backbone.layer3.4.bn1.bias, detector.backbone.layer3.4.bn1.running_mean, detector.backbone.layer3.4.bn1.running_var, detector.backbone.layer3.4.conv2.weight, detector.backbone.layer3.4.bn2.weight, detector.backbone.layer3.4.bn2.bias, detector.backbone.layer3.4.bn2.running_mean, detector.backbone.layer3.4.bn2.running_var, detector.backbone.layer3.4.conv3.weight, detector.backbone.layer3.4.bn3.weight, detector.backbone.layer3.4.bn3.bias, detector.backbone.layer3.4.bn3.running_mean, detector.backbone.layer3.4.bn3.running_var, detector.backbone.layer3.5.conv1.weight, detector.backbone.layer3.5.bn1.weight, detector.backbone.layer3.5.bn1.bias, detector.backbone.layer3.5.bn1.running_mean, detector.backbone.layer3.5.bn1.running_var, detector.backbone.layer3.5.conv2.weight, detector.backbone.layer3.5.bn2.weight, detector.backbone.layer3.5.bn2.bias, detector.backbone.layer3.5.bn2.running_mean, detector.backbone.layer3.5.bn2.running_var, detector.backbone.layer3.5.conv3.weight, detector.backbone.layer3.5.bn3.weight, detector.backbone.layer3.5.bn3.bias, detector.backbone.layer3.5.bn3.running_mean, detector.backbone.layer3.5.bn3.running_var, detector.backbone.layer4.0.conv1.weight, detector.backbone.layer4.0.bn1.weight, detector.backbone.layer4.0.bn1.bias, detector.backbone.layer4.0.bn1.running_mean, detector.backbone.layer4.0.bn1.running_var, detector.backbone.layer4.0.conv2.weight, detector.backbone.layer4.0.bn2.weight, detector.backbone.layer4.0.bn2.bias, detector.backbone.layer4.0.bn2.running_mean, detector.backbone.layer4.0.bn2.running_var, detector.backbone.layer4.0.conv3.weight, detector.backbone.layer4.0.bn3.weight, detector.backbone.layer4.0.bn3.bias, detector.backbone.layer4.0.bn3.running_mean, detector.backbone.layer4.0.bn3.running_var, detector.backbone.layer4.0.downsample.0.weight, detector.backbone.layer4.0.downsample.1.weight, detector.backbone.layer4.0.downsample.1.bias, detector.backbone.layer4.0.downsample.1.running_mean, detector.backbone.layer4.0.downsample.1.running_var, detector.backbone.layer4.1.conv1.weight, detector.backbone.layer4.1.bn1.weight, detector.backbone.layer4.1.bn1.bias, detector.backbone.layer4.1.bn1.running_mean, detector.backbone.layer4.1.bn1.running_var, detector.backbone.layer4.1.conv2.weight, detector.backbone.layer4.1.bn2.weight, detector.backbone.layer4.1.bn2.bias, detector.backbone.layer4.1.bn2.running_mean, detector.backbone.layer4.1.bn2.running_var, detector.backbone.layer4.1.conv3.weight, detector.backbone.layer4.1.bn3.weight, detector.backbone.layer4.1.bn3.bias, detector.backbone.layer4.1.bn3.running_mean, detector.backbone.layer4.1.bn3.running_var, detector.backbone.layer4.2.conv1.weight, detector.backbone.layer4.2.bn1.weight, detector.backbone.layer4.2.bn1.bias, detector.backbone.layer4.2.bn1.running_mean, detector.backbone.layer4.2.bn1.running_var, detector.backbone.layer4.2.conv2.weight, detector.backbone.layer4.2.bn2.weight, detector.backbone.layer4.2.bn2.bias, detector.backbone.layer4.2.bn2.running_mean, detector.backbone.layer4.2.bn2.running_var, detector.backbone.layer4.2.conv3.weight, detector.backbone.layer4.2.bn3.weight, detector.backbone.layer4.2.bn3.bias, detector.backbone.layer4.2.bn3.running_mean, detector.backbone.layer4.2.bn3.running_var, detector.neck.lateral_convs.0.conv.weight, detector.neck.lateral_convs.0.conv.bias, detector.neck.lateral_convs.1.conv.weight, detector.neck.lateral_convs.1.conv.bias, detector.neck.lateral_convs.2.conv.weight, detector.neck.lateral_convs.2.conv.bias, detector.neck.lateral_convs.3.conv.weight, detector.neck.lateral_convs.3.conv.bias, detector.neck.fpn_convs.0.conv.weight, detector.neck.fpn_convs.0.conv.bias, detector.neck.fpn_convs.1.conv.weight, detector.neck.fpn_convs.1.conv.bias, detector.neck.fpn_convs.2.conv.weight, detector.neck.fpn_convs.2.conv.bias, detector.neck.fpn_convs.3.conv.weight, detector.neck.fpn_convs.3.conv.bias, detector.rpn_head.rpn_conv.weight, detector.rpn_head.rpn_conv.bias, detector.rpn_head.rpn_cls.weight, detector.rpn_head.rpn_cls.bias, detector.rpn_head.rpn_reg.weight, detector.rpn_head.rpn_reg.bias, detector.roi_head.bbox_head.fc_cls.weight, detector.roi_head.bbox_head.fc_cls.bias, detector.roi_head.bbox_head.fc_reg.weight, detector.roi_head.bbox_head.fc_reg.bias, detector.roi_head.bbox_head.shared_fcs.0.weight, detector.roi_head.bbox_head.shared_fcs.0.bias, detector.roi_head.bbox_head.shared_fcs.1.weight, detector.roi_head.bbox_head.shared_fcs.1.bias, track_head.track_head.convs.0.conv.weight, track_head.track_head.convs.0.gn.weight, track_head.track_head.convs.0.gn.bias, track_head.track_head.convs.1.conv.weight, track_head.track_head.convs.1.gn.weight, track_head.track_head.convs.1.gn.bias, track_head.track_head.convs.2.conv.weight, track_head.track_head.convs.2.gn.weight, track_head.track_head.convs.2.gn.bias, track_head.track_head.convs.3.conv.weight, track_head.track_head.convs.3.gn.weight, track_head.track_head.convs.3.gn.bias, track_head.track_head.fcs.0.weight, track_head.track_head.fcs.0.bias, track_head.track_head.fc_embed.weight, track_head.track_head.fc_embed.bias
    
    opened by yimingzhou1 1
  • BDD100k det conversion error

    BDD100k det conversion error

    When I try to run this command: python -m bdd100k.label.to_coco -m det -i bdd100k/labels/det_20/det_train.json -o data/bdd/labels/det_20/det_train_cocofmt.json I receive the following error:

    [2022-09-23 16:25:55,619 to_coco.py:301 main] Mode: det remove-ignore: False ignore-as-class: False [2022-09-23 16:25:55,619 to_coco.py:307 main] Loading annotations... [2022-09-23 16:26:02,429 to_coco.py:318 main] Converting annotations... 10%|████████ | 6879/69863 [00:00<00:08, 7435.14it/s] Traceback (most recent call last): File "/u/m/c/mcdougall/miniconda3/envs/torch310/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/u/m/c/mcdougall/miniconda3/envs/torch310/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/u/m/c/mcdougall/miniconda3/envs/torch310/lib/python3.10/site-packages/bdd100k-1.0.0-py3.10.egg/bdd100k/label/to_coco.py", line 337, in main() File "/u/m/c/mcdougall/miniconda3/envs/torch310/lib/python3.10/site-packages/bdd100k-1.0.0-py3.10.egg/bdd100k/label/to_coco.py", line 322, in main coco = bdd100k2coco_det( File "/u/m/c/mcdougall/miniconda3/envs/torch310/lib/python3.10/site-packages/bdd100k-1.0.0-py3.10.egg/bdd100k/label/to_coco.py", line 145, in bdd100k2coco_det if frame["labels"]: KeyError: 'labels'

    This error does not occur when running with ${SET_NAME} equal to val

    opened by IMcDougall 0
  • The reference image and key image are exactly the same

    The reference image and key image are exactly the same

    In the article (QDTrack), the difference between the key image and the reference image is indicated by the image below.

    Screenshot 2022-09-05 113254

    However, when debugging the training code, I saw that the reference image metadata and key image metadata returned by the data loader are exactly the same.

    Screenshot 2022-09-05 103058

    Do I need to change a parameter before starting training or is this an error in the code? I would be glad if you inform me.

    opened by Hcayirli 4
Releases(v0.1)
Owner
ETH VIS Research Group
Visual Intelligence and Systems Group at ETH Zürich
ETH VIS Research Group
Implementation of the CVPR 2021 paper "Online Multiple Object Tracking with Cross-Task Synergy"

Online Multiple Object Tracking with Cross-Task Synergy This repository is the implementation of the CVPR 2021 paper "Online Multiple Object Tracking

null 54 Oct 15, 2022
Python package for multiple object tracking research with focus on laboratory animals tracking.

motutils is a Python package for multiple object tracking research with focus on laboratory animals tracking. Features loads: MOTChallenge CSV, sleap

Matěj Šmíd 2 Sep 5, 2022
git git《Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking》(CVPR 2021) GitHub:git2] 《Masksembles for Uncertainty Estimation》(CVPR 2021) GitHub:git3]

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking Ning Wang, Wengang Zhou, Jie Wang, and Houqiang Li Accepted by CVPR

NingWang 236 Dec 22, 2022
TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

null 912 Jan 8, 2023
Sharpened cosine similarity torch - A Sharpened Cosine Similarity layer for PyTorch

Sharpened Cosine Similarity A layer implementation for PyTorch Install At your c

Brandon Rohrer 203 Nov 30, 2022
[CVPR 2022 Oral] MixFormer: End-to-End Tracking with Iterative Mixed Attention

MixFormer The official implementation of the CVPR 2022 paper MixFormer: End-to-End Tracking with Iterative Mixed Attention [Models and Raw results] (G

Multimedia Computing Group, Nanjing University 235 Jan 3, 2023
PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM

Quasi-Recurrent Neural Network (QRNN) for PyTorch Updated to support multi-GPU environments via DataParallel - see the the multigpu_dataparallel.py ex

Salesforce 1.3k Dec 28, 2022
A python package simulating the quasi-2D pseudospin-1/2 Gross-Pitaevskii equation with NVIDIA GPU acceleration.

A python package simulating the quasi-2D pseudospin-1/2 Gross-Pitaevskii equation with NVIDIA GPU acceleration. Introduction spinor-gpe is high-level,

null 2 Sep 20, 2022
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021.

Dense Contrastive Learning for Self-Supervised Visual Pre-Training This project hosts the code for implementing the DenseCL algorithm for se

Xinlong Wang 491 Jan 3, 2023
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021

Language: 简体中文 | English Introduction This is the code for Multiple Instance Active Learning for Object Detection, CVPR 2021. Installation A Linux pla

Tianning Yuan 269 Dec 21, 2022
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021

MI-AOD Language: 简体中文 | English Introduction This is the code for Multiple Instance Active Learning for Object Detection (The PDF is not available tem

Tianning Yuan 269 Dec 21, 2022
Multiple-Object Tracking with Transformer

TransTrack: Multiple-Object Tracking with Transformer Introduction TransTrack: Multiple-Object Tracking with Transformer Models Training data Training

Peize Sun 537 Jan 4, 2023
Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking (CVPR 2021) Pytorch implementation of the ArTIST motion model. In this repo

Fatemeh 38 Dec 12, 2022
This repository is an official implementation of the paper MOTR: End-to-End Multiple-Object Tracking with TRansformer.

MOTR: End-to-End Multiple-Object Tracking with TRansformer This repository is an official implementation of the paper MOTR: End-to-End Multiple-Object

null 348 Jan 7, 2023
Multiple Object Tracking with Yolov5!

Tracking with yolov5 This implementation is for who need to tracking multi-object only with detector. You can easily track mult-object with your well

null 9 Nov 8, 2022
Yolox-bytetrack-sample - Python sample of MOT (Multiple Object Tracking) using YOLOX and ByteTrack

yolox-bytetrack-sample YOLOXとByteTrackを用いたMOT(Multiple Object Tracking)のPythonサン

KazuhitoTakahashi 12 Nov 9, 2022
Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

Official PyTorch Implementation for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'2021, Oral Presentation) HOTR: End-to-

Kakao Brain 114 Nov 28, 2022