English
Related papers

Related papers: Context-Enhanced Memory-Refined Transformer for On…

200 papers

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Shengjian Wu , Li Sun , Qingli Li

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Jiahui Wang , Zhenyou Wang , Shanna Zhuang , Hui Wang

Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation…

Computer Vision and Pattern Recognition · Computer Science 2018-03-22 Chih-Yao Ma , Asim Kadav , Iain Melvin , Zsolt Kira , Ghassan AlRegib , Hans Peter Graf

Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Song Guo , Jingya Wang , Xinchao Wang , Dacheng Tao

Efficiency is an important issue in designing video architectures for action recognition. 3D CNNs have witnessed remarkable progress in action recognition from videos. However, compared with their 2D counterparts, 3D convolutions often…

Computer Vision and Pattern Recognition · Computer Science 2019-11-22 Zhaoyang Liu , Donghao Luo , Yabiao Wang , Limin Wang , Ying Tai , Chengjie Wang , Jilin Li , Feiyue Huang , Tong Lu

Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Saurabh Sahu , Palash Goyal

Cross-modal video-text retrieval, a challenging task in the field of vision and language, aims at retrieving corresponding instance giving sample from either modality. Existing approaches for this task all focus on how to design encoding…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Rui Zhao , Kecheng Zheng , Zheng-Jun Zha , Hongtao Xie , Jiebo Luo

In the realm of high-frequency data streams, achieving real-time learning within varying memory constraints is paramount. This paper presents Ferret, a comprehensive framework designed to enhance online accuracy of Online Continual Learning…

Machine Learning · Computer Science 2025-03-18 Yuhao Zhou , Yuxin Tian , Jindi Lv , Mingjia Shi , Yuanxi Li , Qing Ye , Shuhao Zhang , Jiancheng Lv

For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Mingyu Wu , Boyuan Jiang , Donghao Luo , Junchi Yan , Yabiao Wang , Ying Tai , Chengjie Wang , Jilin Li , Feiyue Huang , Xiaokang Yang

In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community…

Computer Vision and Pattern Recognition · Computer Science 2019-04-26 Ali Diba , Vivek Sharma , Luc Van Gool , Rainer Stiefelhagen

Transformers have become increasingly popular in offline reinforcement learning (RL) due to their ability to treat agent trajectories as sequences, reframing policy learning as a sequence modeling task. However, in partially observable…

Machine Learning · Computer Science 2026-03-05 Egor Cherepanov , Alexey Staroverov , Alexey K. Kovalev , Aleksandr I. Panov

This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…

Computer Vision and Pattern Recognition · Computer Science 2024-05-15 Matthew Korban , Peter Youngs , Scott T. Acton

Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Qing Zhong , Guodong Ding , Angela Yao

In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze the mutual interactions between linguistic texts and local…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Linchao Zhu , Yi Yang

Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling feature interactions…

Information Retrieval · Computer Science 2024-04-08 Yushen Li , Jinpeng Wang , Tao Dai , Jieming Zhu , Jun Yuan , Rui Zhang , Shu-Tao Xia

Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently…

Artificial Intelligence · Computer Science 2026-02-05 Xiaofeng Lin , Sirou Zhu , Yilei Chen , Mingyu Chen , Hejian Sang , Ioannis Paschalidis , Zhipeng Wang , Aldo Pacchiano , Xuezhou Zhang

Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pre-training language model, has been successful for single-turn machine comprehension, while modeling multiple turns of…

Computation and Language · Computer Science 2019-05-31 Yasuhito Ohsugi , Itsumi Saito , Kyosuke Nishida , Hisako Asano , Junji Tomita

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Mengmeng Wang , Jiazheng Xing , Boyuan Jiang , Jun Chen , Jianbiao Mei , Xingxing Zuo , Guang Dai , Jingdong Wang , Yong Liu

Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Xinyu Yang , Zheheng Jiang , Feixiang Zhou , Yihang Zhu , Na Lv , Nan Xing , Nishan Canagarajah , Huiyu Zhou

Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Yogesh Kumar , Uday Agarwal , Manish Gupta , Anand Mishra