English
Related papers

Related papers: Vision-Language Models Learn Super Images for Effi…

200 papers

State-of-the-art text-video retrieval (TVR) methods typically utilize CLIP and cosine similarity for efficient retrieval. Meanwhile, cross attention methods, which employ a transformer decoder to compute attention between each text query…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Zuozhuo Dai , Fangtao Shao , Qingkun Su , Zilong Dong , Siyu Zhu

The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Yiyi Tao , Zhuoyue Wang , Hang Zhang , Lun Wang

Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Shaojie Zhang , Jiahui Yang , Jianqin Yin , Zhenbo Luo , Jian Luan

Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Zefeng He , Xiaoye Qu , Yafu Li , Siyuan Huang , Daizong Liu , Yu Cheng

Recent advancements in vision-language models have enhanced performance by increasing the length of visual tokens, making them much longer than text tokens and significantly raising computational costs. However, we observe that the visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Senqiao Yang , Yukang Chen , Zhuotao Tian , Chengyao Wang , Jingyao Li , Bei Yu , Jiaya Jia

Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Dezhan Tu , Danylo Vashchilenko , Yuzhe Lu , Panpan Xu

Large-scale vision-language models (VLMs), trained on extensive datasets of image-text pairs, exhibit strong multimodal understanding capabilities by implicitly learning associations between textual descriptions and image regions. This…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Mir Rayat Imtiaz Hossain , Mennatullah Siam , Leonid Sigal , James J. Little

Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension. Complex designs are not uncommon. In this study, we wish to untangle the knots and…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Kelvin C. K. Chan , Xintao Wang , Ke Yu , Chao Dong , Chen Change Loy

Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Nidhi Hegde , Sujoy Paul , Gagan Madan , Gaurav Aggarwal

Current large vision-language models (VLMs) often encounter challenges such as insufficient capabilities of a single visual component and excessively long visual tokens. These issues can limit the model's effectiveness in accurately…

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions. This enrichment…

Computation and Language · Computer Science 2024-07-08 Chang-Sheng Kao , Yun-Nung Chen

Large vision-language models (VLMs) enable joint processing of text and images. However, incorporating vision data significantly increases the prompt length, resulting in a longer time to first token (TTFT). This bottleneck can be…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Tharun Adithya Srikrishnan , Deval Shah , Timothy Hein , Ahmed Hasssan , Stephen Youn , Steven K. Reinhardt

Composed Image Retrieval (CIR) aims to retrieve target images from candidate set using a hybrid-modality query consisting of a reference image and a relative caption that describes the user intent. Recent studies attempt to utilize…

Information Retrieval · Computer Science 2024-12-17 Zelong Sun , Dong Jing , Guoxing Yang , Nanyi Fei , Zhiwu Lu

Text-to-image retrieval aims to find the relevant images based on a text query, which is important in various use-cases, such as digital libraries, e-commerce, and multimedia databases. Although Multimodal Large Language Models (MLLMs)…

Information Retrieval · Computer Science 2024-04-04 Zijun Long , Xuri Ge , Richard Mccreadie , Joemon Jose

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

Visual Question Answering (VQA) models, which fall under the category of vision-language models, conventionally execute multiple downsampling processes on image inputs to strike a balance between computational efficiency and model…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Xirui Zhou , Lianlei Shan , Xiaolin Gui

Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Harry Cheng , Yangyang Guo , Liqiang Nie , Zhiyong Cheng , Mohan Kankanhalli

In a retrieval system, simultaneously achieving search accuracy and efficiency is inherently challenging. This challenge is particularly pronounced in partially relevant video retrieval (PRVR), where incorporating more diverse context…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 WonJun Moon , Cheol-Ho Cho , Woojin Jun , Minho Shim , Taeoh Kim , Inwoong Lee , Dongyoon Wee , Jae-Pil Heo

Stereo video super-resolution (SVSR) aims to enhance the spatial resolution of the low-resolution video by reconstructing the high-resolution video. The key challenges in SVSR are preserving the stereo-consistency and temporal-consistency,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 Hassan Imani , Md Baharul Islam , Lai-Kuan Wong