Kun Dai

Jianhua Yang, Kun Dai

Designing a real-time framework for the spatio-temporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we adopt the existing efficient 3D CNN to save development time. By combining 3D backbones and 2D backbones of different sizes, we design a YOWOv2 family including YOWOv2-Tiny, YOWOv2-Medium, and YOWOv2-Large. We also introduce the popular dynamic label assignment strategy and anchor-free mechanism to make the YOWOv2 consistent with the advanced model architecture design. With our improvement, YOWOv2 is significantly superior to YOWO, and can still keep real-time detection. Without any bells and whistles, YOWOv2 achieves 87.0 % frame mAP and 52.8 % video mAP with over 20 FPS on the UCF101-24. On the AVA, YOWOv2 achieves 21.7 % frame mAP with over 20 FPS. Our code is available on https://github.com/yjh0410/YOWOv2.

Tao Xie, Kun Dai, Ke Wang et al.

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods. The key insight is that local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features. Based on this, we propose a Slimming Transformer (SlimFormer) dedicated for DeepMatcher, which leverages vector-based attention to model relevance among all keypoints and achieves long-range context aggregation in an efficient and effective manner. A relative position encoding is applied to each SlimFormer so as to explicitly disclose relative distance information, further improving the representation of keypoints. A layer-scale strategy is also employed in each SlimFormer to enable the network to assimilate message exchange from the residual block adaptively, thus allowing it to simulate the human behaviour that humans can acquire different matching cues each time they scan an image pair. To facilitate a better adaption of the SlimFormer, we introduce a Feature Transition Module (FTM) to ensure a smooth transition in feature scopes with different receptive fields. By interleaving the self- and cross-SlimFormer multiple times, DeepMatcher can easily establish pixel-wise dense matches at coarse level. Finally, we perceive the match refinement as a combination of classification and regression problems and design Fine Matches Module to predict confidence and offset concurrently, thereby generating robust and accurate matches. Experimentally, we show that DeepMatcher significantly outperforms the state-of-the-art methods on several benchmarks, demonstrating the superior matching capability of DeepMatcher.

Xinyu Zhang, Li Wang, Zhiqiang Jiang et al.

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy. In addition, these methods utilize a conventional handcrafted encoding approach to integrate the positional information of keypoints into the visual descriptors, which limits the capability of the network to extract reliable positional encoding message. In this study, we propose Feature Matching with Reconciliatory Transformer (FMRT), a novel Transformer-based detector-free method that reconciles different features with multiple receptive fields adaptively and utilizes parallel networks to realize reliable positional encoding. Specifically, FMRT proposes a dedicated Reconciliatory Transformer (RecFormer) that consists of a Global Perception Attention Layer (GPAL) to extract visual descriptors with different receptive fields and integrate global context information under various scales, Perception Weight Layer (PWL) to measure the importance of various receptive fields adaptively, and Local Perception Feed-forward Network (LPFFN) to extract deep aggregated multi-scale local feature representation. Extensive experiments demonstrate that FMRT yields extraordinary performance on multiple benchmarks, including pose estimation, visual localization, homography estimation, and image matching.