English
Related papers

Related papers: Query-Dependent Video Representation for Moment Re…

200 papers

Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis. Recent approaches treat MR and HD as similar video grounding problems and address them together with…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Yicheng Xiao , Zhuoyan Luo , Yong Liu , Yue Ma , Hengwei Bian , Yatai Ji , Yujiu Yang , Xiu Li

Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Meng Cao , Long Chen , Mike Zheng Shou , Can Zhang , Yuexian Zou

We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Eslam Mohamed , Ahmad El-Sallab

Recent DEtection TRansformer (DETR) based frameworks have achieved remarkable success in end-to-end object detection. However, the reliance on the Hungarian algorithm for bipartite matching between queries and ground truths introduces…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Shoumeng Qiu , Xinrun Li , Yang Long

Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and then predict 3D attributes by neighboring features. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Renrui Zhang , Han Qiu , Tai Wang , Ziyu Guo , Yiwen Tang , Xuanzhuo Xu , Ziteng Cui , Yu Qiao , Peng Gao , Hongsheng Li

Video-text retrieval (VTR) aims to locate relevant videos using natural language queries. Current methods, often based on pre-trained models like CLIP, are hindered by video's inherent redundancy and their reliance on coarse, final-layer…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Zequn Xie , Boyun Zhang , Yuxiao Lin , Tao Jin

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Depu Meng , Xiaokang Chen , Zejia Fan , Gang Zeng , Houqiang Li , Yuhui Yuan , Lei Sun , Jingdong Wang

Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Jue Wang , Lorenzo Torresani

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Feng Li , Hao Zhang , Shilong Liu , Jian Guo , Lionel M. Ni , Lei Zhang

Detecting video moments and highlights from natural-language queries have been unified by transformer-based methods. Other works use generative Multimodal LLM (MLLM) to predict moments and/or highlights as text timestamps, utilizing its…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 I Putu Andika Bagas Jiwanta , Ayu Purwarianti

Identifying highlight moments of raw video materials is crucial for improving the efficiency of editing videos that are pervasive on internet platforms. However, the extensive work of manually labeling footage has created obstacles to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Tingtian Li , Zixun Sun , Xinyu Xiao

With the emergence of VR and AR, 360{\deg} data attracts increasing attention from the computer vision and multimedia communities. Typically, 360{\deg} data is projected into 2D ERP (equirectangular projection) images for feature…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Yinjie Zhao , Lichen Zhao , Qian Yu , Jing Zhang , Lu Sheng , Dong Xu

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Fengyuan Shi , Ruopeng Gao , Weilin Huang , Limin Wang

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Aishwarya Kamath , Mannat Singh , Yann LeCun , Gabriel Synnaeve , Ishan Misra , Nicolas Carion

Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge information and aggregating multi-level features to improve SOD performance. To achieve satisfactory performance, the methods employ refined…

Computer Vision and Pattern Recognition · Computer Science 2022-06-28 Min Seok Lee , Wooseok Shin , Sung Won Han

We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression…

Computer Vision and Pattern Recognition · Computer Science 2020-05-29 Nicolas Carion , Francisco Massa , Gabriel Synnaeve , Nicolas Usunier , Alexander Kirillov , Sergey Zagoruyko

Temporal Moment Localization (TML) in untrimmed videos is a challenging task in the field of multimedia, which aims at localizing the start and end points of the activity in the video, described by a sentence query. Existing methods mainly…

Multimedia · Computer Science 2021-11-02 Ziyang Ma , Xianjing Han , Xuemeng Song , Yiran Cui , Liqiang Nie

Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect extremely small-sized objects, some of which occupy a smaller than one-pixel area. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Zhaoxu Li , Wei An , Gaowei Guo , Longguang Wang , Yingqian Wang , Zaiping Lin

State-of-the-art handwritten text recognition (HTR) systems commonly use Transformers, whose growing key-value (KV) cache makes decoding slow and memory-intensive. We introduce DRetHTR, a decoder-only model built on Retentive Networks…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Changhun Kim , Martin Mayr , Thomas Gorges , Fei Wu , Mathias Seuret , Andreas Maier , Vincent Christlein

Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance. This paper first studies the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Qiang Wang , Yanhao Zhang , Yun Zheng , Pan Pan , Xian-Sheng Hua