English
Related papers

Related papers: HTTM: Head-wise Temporal Token Merging for Faster …

200 papers

This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jun Zhang , Teng Wang , Yuying Ge , Yixiao Ge , Xinhao Li , Ying Shan , Limin Wang

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Jusheng Zhang , Xiaoyang Guo , Kaitong Cai , Qinhan Lv , Yijia Fan , Wenhao Chai , Jian Wang , Keze Wang

Current multi-view indoor 3D object detectors rely on sensor geometry that is costly to obtain (i.e., precisely calibrated multi-view camera poses) to fuse multi-view information into a global scene representation, limiting deployment in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yang Cao , Feize Wu , Dave Zhenyu Chen , Yingji Zhong , Lanqing Hong , Dan Xu

The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction without per-scene optimization. However, its billion-parameter scale creates high memory and compute demands, hindering on-device deployment.…

Hardware Architecture · Computer Science 2026-01-29 Yipu Zhang , Jintao Cheng , Xingyu Liu , Zeyu Li , Carol Jingyi Li , Jin Wu , Lin Jiang , Yuan Xie , Jiang Xu , Wei Zhang

Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders inference efficiency, and prior studies have shown that many…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Jingqi Xu , Jingxi Lu , Chenghao Li , Sreetama Sarkar , Peter A. Beerel

Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Sicheng Zuo , Zixun Xie , Wenzhao Zheng , Shaoqing Xu , Fang Li , Shengyin Jiang , Long Chen , Zhi-Xin Yang , Jiwen Lu

Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Tao Pu , Tianshui Chen , Hefeng Wu , Yongyi Lu , Liang Lin

Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xianbing Sun , Zhikai Zhu , Zhengyu Lou , Bo Yang , Jinyang Tang , Liqing Zhang , He Wang , Jianfu Zhang

Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging methods improve…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Min-Jeong Lee , Hee-Dong Kim , Seong-Whan Lee

Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Zhihang Lin , Mingbao Lin , Luxi Lin , Rongrong Ji

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Shuhong Zheng , Michael Oechsle , Erik Sandström , Marie-Julie Rakotosaona , Federico Tombari , Igor Gilitschenski

Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions, enabling coherent and accurate understanding of complex scenes. However, most prior approaches prioritize training large…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Hao Li , Zhengyu Zou , Fangfu Liu , Xuanyang Zhang , Fangzhou Hong , Yukang Cao , Yushi Lan , Manyuan Zhang , Gang Yu , Dingwen Zhang , Ziwei Liu

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Daniel Kienzle , Marco Kantonis , Robin Schön , Rainer Lienhart

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Tianchen Deng , Wenhua Wu , Kunzhen Wu , Guangming Wang , Siting Zhu , Shenghai Yuan , Xun Chen , Guole Shen , Zhe Liu , Hesheng Wang

Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the denoising process among similar tokens have been introduced.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Haipeng Fang , Sheng Tang , Juan Cao , Enshuo Zhang , Fan Tang , Tong-Yee Lee

While 3D Multi-modal Large Language Models (MLLMs) demonstrate remarkable scene understanding capabilities, their practical deployment faces critical challenges due to computational inefficiency. The key bottleneck stems from processing…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Wencan Huang , Daizong Liu , Wei Hu

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Zhenhailong Wang , Senthil Purushwalkam , Caiming Xiong , Silvio Savarese , Heng Ji , Ran Xu

This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Peng Ye , Chenyu Huang , Mingzhu Shen , Tao Chen , Yongqi Huang , Yuning Zhang , Wanli Ouyang

Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer from heavy computational costs induced by the massive number…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Joonmyung Choi , Sanghyeok Lee , Jaewon Chu , Minhyuk Choi , Hyunwoo J. Kim