English
Related papers

Related papers: Structured Video Tokens @ Ego4D PNR Temporal Local…

200 papers

Video temporal grounding (VTG) aims to localize the start and end timestamps of the event described by a given query within an untrimmed video. Despite the strong open-world video understanding and recognition ability of video language…

Multimedia · Computer Science 2026-05-05 Pengcheng Fang , Yuxia Chen , Xiaohao Cai

Pretraining egocentric vision-language models has become essential to improving downstream egocentric video-text tasks. These egocentric foundation models commonly use the transformer architecture. The memory footprint of these models…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Hector A. Valdez , Kyle Min , Subarna Tripathi

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Lu He , Qianyu Zhou , Xiangtai Li , Li Niu , Guangliang Cheng , Xiao Li , Wenxuan Liu , Yunhai Tong , Lizhuang Ma , Liqing Zhang

The recently released Ego4D dataset and benchmark significantly scales and diversifies the first-person visual perception data. In Ego4D, the Visual Queries 2D Localization task aims to retrieve objects appeared in the past from the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-04 Mengmeng Xu , Cheng-Yang Fu , Yanghao Li , Bernard Ghanem , Juan-Manuel Perez-Rua , Tao Xiang

In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Xin Gu , Bing Fan , Jiali Yao , Zhipeng Zhang , Yan Huang , Cheng Han , Heng Fan , Libo Zhang

How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus on designing a complicated appearance model or template…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Liangtao Shi , Bineng Zhong , Qihua Liang , Ning Li , Shengping Zhang , Xianxian Li

In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Yisen Feng , Haoyu Zhang , Yuquan Xie , Zaijing Li , Meng Liu , Liqiang Nie

Videos are a rich source for self-supervised learning (SSL) of visual representations due to the presence of natural temporal transformations of objects. However, current methods typically randomly sample video clips for learning, which…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Brian Chen , Ramprasaath R. Selvaraju , Shih-Fu Chang , Juan Carlos Niebles , Nikhil Naik

Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Jianrui Zhang , Yue Yang , Rohun Tripathi , Winson Han , Ranjay Krishna , Christopher Clark , Yong Jae Lee , Sangho Lee

Spatio-temporal video grounding (STVG) aims to localize queried objects within dynamic video segments. Prevailing fully-trained approaches are notoriously data-hungry. However, gathering large-scale STVG data is exceptionally challenging:…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Zanyi Wang , Fan Li , Dengyang Jiang , Liuzhuozheng Li , Yunhua Zhong , Guang Dai , Mengmeng Wang

Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Shi-Xue Zhang , Hongfa Wang , Xiaobin Zhu , Weibo Gu , Tianjin Zhang , Chun Yang , Wei Liu , Xu-Cheng Yin

Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" reasoning over frames sampled at high temporal resolution.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Mattia Soldan , Fabian Caba Heilbron , Bernard Ghanem , Josef Sivic , Bryan Russell

The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Rachid Reda Dokkar , Faten Chaieb , Hassen Drira , Arezki Aberkane

We present a single neural network architecture composed of task-agnostic components (ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav ("go to location in <this picture>") and ObjectNav ("find a chair")…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Karmesh Yadav , Arjun Majumdar , Ram Ramrakhya , Naoki Yokoyama , Alexei Baevski , Zsolt Kira , Oleksandr Maksymets , Dhruv Batra

Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Yifan Xu , Zhijie Zhang , Mengdan Zhang , Kekai Sheng , Ke Li , Weiming Dong , Liqing Zhang , Changsheng Xu , Xing Sun

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Quan Kong , Yanru Xiao , Yuhao Shen , Cong Wang

Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with…

Computer Vision and Pattern Recognition · Computer Science 2022-12-16 Liqi Yan , Qifan Wang , Siqi Ma , Jingang Wang , Changbin Yu

High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fundamental capabilities to facilitate closed-loop training.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Bowyn Tan , Yutong Xie , Bai Huang , Fan Luo , Xiao Li , Naizheng Wang , Yang Guan , Shengbo Eben Li

This paper presents an approach for Evoked Expressions from Videos (EEV) challenge, which aims to predict evoked facial expressions from video. We take advantage of pre-trained models on large-scale datasets in computer vision and audio…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 VanThong Huynh , Guee-Sang Lee , Hyung-Jeong Yang , Soo-Huyng Kim

Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Huanjin Yao , Wenhao Wu , Zhiheng Li