English
Related papers

Related papers: Masked Diffusion Vision-Language Models for Tempor…

200 papers

Causal attention has become a foundational mechanism in autoregressive vision-language models (VLMs), unifying textual and visual inputs under a single generative framework. However, existing causal mask-based strategies are inherited from…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Xiaohuan Pei , Tao Huang , YanXiang Ma , Chang Xu

Human action recognition in long-term videos, characterized by complex backgrounds and subtle action differences, poses significant challenges for traditional deep learning models due to computational overhead, difficulty in capturing…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Kaining Li , Shuwei He , Zihan Xu

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

The goal of Multilingual Visual Answer Localization (MVAL) is to locate a video segment that answers a given multilingual question. Existing methods either focus solely on visual modality or integrate visual and subtitle modalities.…

Multimedia · Computer Science 2024-11-06 Zhibin Wen , Bin Li

Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence…

Computation and Language · Computer Science 2026-02-24 Xinhao Sun , Huaijin Zhao , Maoliang Li , Zihao Zheng , Jiayu Chen , Yun Liang , Xiang Chen

Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evidence to be integrated without explicit reasoning tokens. However, we identify a…

Machine Learning · Computer Science 2026-05-05 Xin Zhang , Qiqi Tao , Jiawei Du , Moyun Liu , Joey Tianyi Zhou

Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Edward Fish , Jon Weinbren , Andrew Gilbert

The vocabulary size in temporal action localization (TAL) is limited by the scarcity of large-scale annotated datasets. To overcome this, recent works integrate vision-language models (VLMs), such as CLIP, for open-vocabulary TAL (OV-TAL).…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Jeongseok Hyun , Su Ho Han , Hyolim Kang , Joon-Young Lee , Seon Joo Kim

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Jike Zhong , Yuxiang Lai , Xiaofeng Yang , Konstantinos Psounis

Temporal language grounding (TLG) is a fundamental and challenging problem for vision and language understanding. Existing methods mainly focus on fully supervised setting with temporal boundary labels for training, which, however, suffers…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Yuechen Wang , Jiajun Deng , Wengang Zhou , Houqiang Li

We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Sanjay Haresh , Sateesh Kumar , Huseyin Coskun , Shahram Najam Syed , Andrey Konin , Muhammad Zeeshan Zia , Quoc-Huy Tran

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the…

Artificial Intelligence · Computer Science 2026-05-28 Jeong Hun Yeo , Chae Won Kim , Hyeongseop Rha , Yong Man Ro

Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content. Given limited GPU memory, training TAL end to end (i.e., from videos to predictions) on long videos is a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Chen Zhao , Shuming Liu , Karttikeya Mangalam , Bernard Ghanem

We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a…

Computer Vision and Pattern Recognition · Computer Science 2023-07-17 Sauradip Nag , Xiatian Zhu , Jiankang Deng , Yi-Zhe Song , Tao Xiang

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Lijun Yu

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Minghang Zheng , Xinhao Cai , Qingchao Chen , Yuxin Peng , Yang Liu

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Machine Learning · Computer Science 2025-03-27 Yuncheng Guo , Xiaodong Gu

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Machine Learning · Computer Science 2026-02-18 Nicolas Buzeta , Felipe del Rio , Cristian Hinostroza , Denis Parra , Hans Lobel , Rodrigo Toro Icarte

Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chaolei Han , Hongsong Wang , Xin Gong , Jie Gui

Temporal action localization (TAL), which involves recognizing and locating action instances, is a challenging task in video understanding. Most existing approaches directly predict action classes and regress offsets to boundaries, while…

Computer Vision and Pattern Recognition · Computer Science 2023-09-14 Jiayi Shao , Xiaohan Wang , Ruijie Quan , Junjun Zheng , Jiang Yang , Yi Yang