English
Related papers

Related papers: A Solution to CVPR'2023 AQTC Challenge: Video Alig…

200 papers

Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Qi Wang , Yanrui Yu , Ye Yuan , Rui Mao , Tianfei Zhou

Vision-language pretraining models have made significant progress in bridging remote sensing imagery with natural language. However, existing approaches often fail to effectively integrate multi-granular visual and textual information,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xiao Yang , Ronghao Fu , Zhuoran Duan , Zhiwen Lin , Xueyan Liu , Bo Yang

Parameter-Efficient Fine-Tuning (PEFT) has emerged to mitigate the computational demands of large-scale models. Within computer vision, adapter-based PEFT methods are often favored over prompt-based approaches like Visual Prompt Tuning…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Lingyun Huang , Jianxu Mao , Junfei Yi , Ziming Tao , Yaonan Wang

In this paper, we introduce a grounded video question-answering solution. Our research reveals that the fixed official baseline method for video question answering involves two main steps: visual grounding and object tracking. However, a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Hailiang Zhang , Dian Chao , Zhihao Guan , Yang Yang

Deep neural networks require collecting and annotating large amounts of data to train successfully. In order to alleviate the annotation bottleneck, we propose a novel self-supervised representation learning approach for spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2019-10-29 Alaaeldin El-Nouby , Shuangfei Zhai , Graham W. Taylor , Joshua M. Susskind

We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label…

Computer Vision and Pattern Recognition · Computer Science 2016-07-29 De-An Huang , Li Fei-Fei , Juan Carlos Niebles

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Zheng Li , Yibing Song , Ming-Ming Cheng , Xiang Li , Jian Yang

Text-to-video retrieval systems have recently made significant progress by utilizing pre-trained models trained on large-scale image-text pairs. However, most of the latest methods primarily focus on the video modality while disregarding…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Sarah Ibrahimi , Xiaohang Sun , Pichao Wang , Amanmeet Garg , Ashutosh Sanan , Mohamed Omar

Instructional videos provide a convenient modality to learn new tasks (ex. cooking a recipe, or assembling furniture). A viewer will want to find a corresponding video that reflects both the overall task they are interested in as well as…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Karan Samel , Nitish Sontakke , Irfan Essa

Manual spatio-temporal annotation of human action in videos is laborious, requires several annotators and contains human biases. In this paper, we present a weakly supervised approach to automatically obtain spatio-temporal annotations of…

Computer Vision and Pattern Recognition · Computer Science 2016-05-27 Waqas Sultani , Mubarak Shah

Video annotation is expensive and time consuming. Consequently, datasets for multi-person pose estimation and tracking are less diverse and have more sparse annotations compared to large scale image datasets for human pose estimation. This…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Umer Rafi , Andreas Doering , Bastian Leibe , Juergen Gall

Detecting transitions between intro/credits and main content in videos is a crucial task for content segmentation, indexing, and recommendation systems. Manual annotation of such transitions is labor-intensive and error-prone, while…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Vasilii Korolkov , Andrey Yanchenko

We pose keystep recognition as a node classification task, and propose a flexible graph-learning framework for fine-grained keystep recognition that is able to effectively leverage long-term dependencies in egocentric videos. Our approach,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Julia Lee Romero , Kyle Min , Subarna Tripathi , Morteza Karimzadeh

The WWW 2025 EReL@MIR Workshop Multimodal CTR Prediction Challenge focuses on effectively applying multimodal embedding features to improve click-through rate (CTR) prediction in recommender systems. This technical report presents our…

Information Retrieval · Computer Science 2025-05-07 Junwei Xu , Zehao Zhao , Xiaoyu Hu , Zhenjie Song

Visual Planning for Assistance (VPA) aims to predict a sequence of user actions required to achieve a specified goal based on a video showing the user's progress. Although recent advances in multimodal large language models (MLLMs) have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Ce Zhang , Yale Song , Ruta Desai , Michael Louis Iuzzolino , Joseph Tighe , Gedas Bertasius , Satwik Kottur

This paper proposes a single-stage training approach that semantically aligns three modalities - audio, visual, and text using a contrastive learning framework. Contrastive training has gained prominence for multimodal alignment, utilizing…

Sound · Computer Science 2025-05-21 Parthasaarathy Sudarsanam , Irene Martín-Morató , Tuomas Virtanen

Knowledge tracing (KT) is a popular approach for modeling students' learning progress over time, which can enable more personalized and adaptive learning. However, existing KT approaches face two major limitations: (1) they rely heavily on…

Machine Learning · Computer Science 2025-03-14 Yilmazcan Ozyurt , Stefan Feuerriegel , Mrinmaya Sachan

Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Nan Zhou , Jiaxin Chen , Di Huang

Multimodal large language models (MLLMs) are flourishing, but mainly focus on images with less attention than videos, especially in sub-fields such as prompt engineering, video chain-of-thought (CoT), and instruction tuning on videos.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Yan Wang , Yawen Zeng , Jingsheng Zheng , Xiaofen Xing , Jin Xu , Xiangmin Xu

Despite the rapid progress of instruction-based image editing, its extension to video remains underexplored, primarily due to the prohibitive cost and complexity of constructing large-scale paired video editing datasets. To address this…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Xinyao Liao , Xianfang Zeng , Ziye Song , Zhoujie Fu , Gang Yu , Guosheng Lin