This technical report presents our solution for temporal action detection task in AcitivityNet Challenge 2021. The purpose of this task is to locate and identify actions of interest in long untrimmed videos. The crucial challenge of the task comes from that the temporal duration of action varies dramatically, and the target actions are typically embedded in a background of irrelevant activities. Our solution builds on BMN, and mainly contains three steps: 1) action classification and feature encoding by Slowfast, CSN and ViViT; 2) proposal generation. We improve BMN by embedding the proposed Proposal Relation Network (PRN), by which we can generate proposals of high quality; 3) action detection. We calculate the detection results by assigning the proposals with corresponding classification results. Finally, we ensemble the results under different settings and achieve 44.7% on the test set, which improves the champion result in ActivityNet 2020 by 1.9% in terms of average mAP.
This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.
This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop. The goal of our task is to locate the start time and the end time of the action in the long untrimmed video, and predict action category. We adopt sliding window strategy to generate proposals, which can better adapt to short-duration actions. In addition, we show that classification and proposals are conflict in the same network. The separation of the two tasks boost the detection performance with high efficiency. By simply employing these strategy, we achieved 16.10\% performance on the test set of EPIC-KITCHENS-100 Action Detection challenge using a single model, surpassing the baseline method by 11.7\% in terms of average mAP.
With the recent surge in the research of vision transformers, they have demonstrated remarkable potential for various challenging computer vision applications, such as image recognition, point cloud classification as well as video understanding. In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset. Specifically, we explore training techniques for video vision transformers, such as augmentations, resolutions as well as initialization, etc. With our training recipe, a single ViViT model achieves the performance of 47.4\% on the validation set of EPIC-KITCHENS-100 dataset, outperforming what is reported in the original paper by 3.4%. We found that video transformers are especially good at predicting the noun in the verb-noun action prediction task. This makes the overall action prediction accuracy of video transformers notably higher than convolutional ones. Surprisingly, even the best video transformers underperform the convolutional networks on the verb prediction. Therefore, we combine the video vision transformers and some of the convolutional video networks and present our solution to the EPIC-KITCHENS-100 Action Recognition competition.
Exploiting multi-scale features has shown great potential in tackling semantic segmentation problems. The aggregation is commonly done with sum or concatenation (concat) followed by convolutional (conv) layers. However, it fully passes down the high-level context to the following hierarchy without considering their interrelation. In this work, we aim to enable the low-level feature to aggregate the complementary context from adjacent high-level feature maps by a cross-scale pixel-to-region relation operation. We leverage cross-scale context propagation to make the long-range dependency capturable even by the high-resolution low-level features. To this end, we employ an efficient feature pyramid network to obtain multi-scale features. We propose a Relational Semantics Extractor (RSE) and Relational Semantics Propagator (RSP) for context extraction and propagation respectively. Then we stack several RSP into an RSP head to achieve the progressive top-down distribution of the context. Experiment results on two challenging datasets Cityscapes and COCO demonstrate that the RSP head performs competitively on both semantic segmentation and panoptic segmentation with high efficiency. It outperforms DeeplabV3 [1] by 0.7% with 75% fewer FLOPs (multiply-adds) in the semantic segmentation task.
Motions are reflected in videos as the movement of pixels, and actions are essentially patterns of inconsistent motions between the foreground and the background. To well distinguish the actions, especially those with complicated spatio-temporal interactions, correctly locating the prominent motion areas is of crucial importance. However, most motion information in existing videos are difficult to label and training a model with good motion representations with supervision will thus require a large amount of human labour for annotation. In this paper, we address this problem by self-supervised learning. Specifically, we propose to learn Motion from Static Images (MoSI). The model learns to encode motion information by classifying pseudo motions generated by MoSI. We furthermore introduce a static mask in pseudo motions to create local motion patterns, which forces the model to additionally locate notable motion areas for the correct classification.We demonstrate that MoSI can discover regions with large motion even without fine-tuning on the downstream datasets. As a result, the learned motion representations boost the performance of tasks requiring understanding of complex scenes and motions, i.e., action recognition. Extensive experiments show the consistent and transferable improvements achieved by MoSI. Codes will be soon released.
Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail to deal with this problem because of (1) lacking of usage of temporal information; (2) lacking of training data in crowded scenes. In this paper, we focus on improving human pose estimation in videos of crowded scenes from the perspectives of exploiting temporal context and collecting new data. In particular, we first follow the top-down strategy to detect persons and perform single-person pose estimation for each frame. Then, we refine the frame-based pose estimation with temporal contexts deriving from the optical-flow. Specifically, for one frame, we forward the historical poses from the previous frames and backward the future poses from the subsequent frames to current frame, leading to stable and accurate human pose estimation in videos. In addition, we mine new data of similar scenes to HIE dataset from the Internet for improving the diversity of training set. In this way, our model achieves best performance on 7 out of 13 videos and 56.33 average w\_AP on test dataset of HIE challenge.
This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events. Remarkable progress has been made in multi-pose training in recent years. However, how to track the human pose in crowded and complex environments has not been well addressed. We formulate the problem as several subproblems to be solved. First, we use a multi-object tracking method to assign human ID to each bounding box generated by the detection model. After that, a pose is generated to each bounding box with ID. At last, optical flow is used to take advantage of the temporal information in the videos and generate the final pose tracking result.
Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes. In this paper, we focus on improving spatio-temporal action recognition by fully-utilizing the information of scenes and collecting new data. A top-down strategy is used to overcome the limitations. Specifically, we adopt a strong human detector to detect the spatial location of each frame. We then apply action recognition models to learn the spatio-temporal information from video frames on both the HIE dataset and new data with diverse scenes from the internet, which can improve the generalization ability of our model. Besides, the scenes information is extracted by the semantic segmentation model to assistant the process. As a result, our method achieved an average 26.05 wf\_mAP (ranking 1st place in the ACM MM grand challenge 2020: Human in Events).
In recent years, self-supervised methods for monocular depth estimation has rapidly become an significant branch of depth estimation task, especially for autonomous driving applications. Despite the high overall precision achieved, current methods still suffer from a) imprecise object-level depth inference and b) uncertain scale factor. The former problem would cause texture copy or provide inaccurate object boundary, and the latter would require current methods to have an additional sensor like LiDAR to provide depth groundtruth or stereo camera as additional training inputs, which makes them difficult to implement. In this work, we propose to address these two problems together by introducing DNet. Our contributions are twofold: a) a novel dense connected prediction (DCP) layer is proposed to provide better object-level depth estimation and b) specifically for autonomous driving scenarios, dense geometrical constrains (DGC) is introduced so that precise scale factor can be recovered without additional cost for autonomous vehicles. Extensive experiments have been conducted and, both DCP layer and DGC module are proved to be effectively solving the aforementioned problems respectively. Thanks to DCP layer, object boundary can now be better distinguished in the depth map and the depth is more continues on object level. It is also demonstrated that the performance of using DGC to perform scale recovery is comparable to that using ground-truth information, when the camera height is given and the ground point takes up more than 1.03% of the pixels. Code will be publicly available once the paper is accepted.