English
Related papers

Related papers: Cross-modal Causal Relation Alignment for Video Qu…

200 papers

Despite recent progress towards scaling up multimodal vision-language models, these models are still known to struggle on compositional generalization benchmarks such as Winoground. We find that a critical component lacking from current…

Computation and Language · Computer Science 2023-07-06 Rohan Pandey , Rulin Shao , Paul Pu Liang , Ruslan Salakhutdinov , Louis-Philippe Morency

Grounded video question answering (GVQA) aims to localize relevant temporal segments in videos and generate accurate answers to a given question; however, large video-language models (LVLMs) exhibit limited temporal awareness. Although…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Xiaoqian Shen , Min-Hung Chen , Yu-Chiang Frank Wang , Mohamed Elhoseiny , Ryo Hachiuma

We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2021-06-04 Xun Yang , Fuli Feng , Wei Ji , Meng Wang , Tat-Seng Chua

Knowledge-based visual question answering (KB-VQA) demonstrates significant potential for handling knowledge-intensive tasks. However, conflicts arise between static parametric knowledge in vision language models (VLMs) and dynamically…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Yuyang Hong , Jiaqi Gu , Yujin Lou , Lubin Fan , Qi Yang , Ying Wang , Kun Ding , Yue Wu , Shiming Xiang , Jieping Ye

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Mingfang Zhang , Jingjing Pan , Ashutosh Kumar , Rajat Saini , Mustafa Erdogan , Hsuan-Kung Yang , Caixin Kang , Yifei Huang , Yoichi Sato , Quan Kong

Visual events are a composition of temporal actions involving actors spatially interacting with objects. When developing computer vision models that can reason about compositional spatio-temporal events, we need benchmarks that can analyze…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Madeleine Grunde-McLaughlin , Ranjay Krishna , Maneesh Agrawala

Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and suboptimal performance. We propose Consistent Cross-layer…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Yifan Wang , Hongfeng Ai , Quangao Liu , Maowei Jiang , Ruiyuan Kang , Ruiqi Li , Jiahua Dong , Mengting Xiao , Cheng Jiang , Chenzhong Li

Significant progress has been made in the field of video question answering (VideoQA) thanks to deep learning and large-scale pretraining. Despite the presence of sophisticated model structures and powerful video-text foundation models,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Haopeng Li , Tom Drummond , Mingming Gong , Mohammed Bennamoun , Qiuhong Ke

This paper strives to solve complex video question answering (VideoQA) which features long video containing multiple objects and events at different time. To tackle the challenge, we highlight the importance of identifying question-critical…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Yicong Li , Junbin Xiao , Chun Feng , Xiang Wang , Tat-Seng Chua

We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Junbin Xiao , Xindi Shang , Angela Yao , Tat-Seng Chua

Cross-lingual Cross-modal Retrieval (CCR) is an essential task in web search, which aims to break the barriers between modality and language simultaneously and achieves image-text retrieval in the multi-lingual scenario with a single model.…

Information Retrieval · Computer Science 2024-06-27 Zhijie Nie , Richong Zhang , Zhangchi Feng , Hailang Huang , Xudong Liu

A video-grounded dialogue system referred to as the Structured Co-reference Graph Attention (SCGA) is presented for decoding the answer sequence to a question regarding a given video while keeping track of the dialogue context. Although…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Junyeong Kim , Sunjae Yoon , Dahyun Kim , Chang D. Yoo

Video Question Answering (VideoQA) is a challenging video understanding task since it requires a deep understanding of both question and video. Previous studies mainly focus on extracting sophisticated visual and language embeddings, fusing…

Computer Vision and Pattern Recognition · Computer Science 2021-05-17 Fangtao Li , Ting Bai , Chenyu Cao , Zihe Liu , Chenghao Yan , Bin Wu

Medical Visual Question Answering (MedVQA) aims to answer medical questions according to medical images. However, the complexity of medical data leads to confounders that are difficult to observe, so bias between images and questions is…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Zibo Xu , Qiang Li , Weizhi Nie , Weijie Wang , Anan Liu

In this paper, we propose a method to obtain robust explanations for visual question answering(VQA) that correlate well with the answers. Our model explains the answers obtained through a VQA model by providing visual and textual…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Badri N. Patro , Shivansh Pate , Vinay P. Namboodiri

We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question, we generate an open-ended answer grounded with the start and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Ayush Gupta , Anirban Roy , Rama Chellappa , Nathaniel D. Bastian , Alvaro Velasquez , Susmit Jha

The current success of modern visual reasoning systems is arguably attributed to cross-modality attention mechanisms. However, in deliberative reasoning such as in VQA, attention is unconstrained at each step, and thus may serve as a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Thao Minh Le , Vuong Le , Sunil Gupta , Svetha Venkatesh , Truyen Tran

Audio-visual question answering (AVQA) is a challenging task that requires multistep spatio-temporal reasoning over multimodal contexts. Recent works rely on elaborate target-agnostic parsing of audio-visual scenes for spatial grounding…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Yuanyuan Jiang , Jianqin Yin

Multimodal question answering (QA) often requires identifying which video, audio, or sensor tokens are relevant to the question. Yet modality disagreements are common: off-camera speech, background noise, or motion outside the field of view…

Computation and Language · Computer Science 2025-09-08 Subrata Biswas , Mohammad Nur Hossain Khan , Bashima Islam

Grounded Video Question Answering (Grounded VideoQA) requires aligning textual answers with explicit visual evidence. However, modern multimodal models often rely on linguistic priors and spurious correlations, resulting in poorly grounded…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Jisheng Dang , Huilin Song , Junbin Xiao , Bimei Wang , Han Peng , Haoxuan Li , Xun Yang , Meng Wang , Tat-Seng Chua