English
Related papers

Related papers: Make Your Training Flexible: Towards Deployment-Ef…

200 papers

Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Soroush Mahdi , Fardin Ayar , Ehsan Javanmardi , Manabu Tsukada , Mahdi Javanmardi

Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Zheng , Jieyu Zhang , Jianing Zhang , Weikai Huang , Ashutosh Kumar , Quan Kong , Oncel Tuzel , Chun-Liang Li , Ranjay Krishna

Temporal quality is a critical aspect of video generation, as it ensures consistent motion and realistic dynamics across frames. However, achieving high temporal coherence and diversity remains challenging. In this work, we explore temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Harold Haodong Chen , Haojian Huang , Xianfeng Wu , Yexin Liu , Yajing Bai , Wen-Jie Shu , Harry Yang , Ser-Nam Lim

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Ayush K. Rai , Kyle Min , Tarun Krishna , Feiyan Hu , Alan F. Smeaton , Noel E. O'Connor

Despite the remarkable success of Vision Transformers (ViTs) in various visual tasks, they are often hindered by substantial computational cost. In this work, we introduce Vote\&Mix (\textbf{VoMix}), a plug-and-play and parameter-free token…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Shuai Peng , Di Fu , Baole Wei , Yong Cao , Liangcai Gao , Zhi Tang

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Vatsal Agarwal , Saksham Suri , Matthew Gwilliam , Pulkit Kumar , Abhinav Shrivastava

Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher accuracy at greater computational cost, but changing the…

Recent studies in long video understanding have harnessed the advanced visual-language reasoning capabilities of Large Multimodal Models (LMMs), driving the evolution of video-LMMs specialized for processing extended video sequences.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Janghoon Cho , Jungsoo Lee , Munawar Hayat , Kyuwoong Hwang , Fatih Porikli , Sungha Choi

Video question answering benefits from the rich information in videos, enabling various applications. However, the large volume of tokens generated from long videos presents challenges to memory efficiency and model performance. To…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Yumeng Shi , Quanyu Long , Wenya Wang

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Xinjian Wu , Fanhu Zeng , Xiudong Wang , Xinghao Chen

Video tokenization procedure is critical for a wide range of video processing tasks. Most existing approaches directly transform video into fixed-grid and patch-wise tokens, which exhibit limited versatility. Spatially, uniformly allocating…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Zhenghao Chen , Zicong Chen , Lei Liu , Yiming Wu , Dong Xu

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Mingbao Lin , Mengzhao Chen , Yuxin Zhang , Chunhua Shen , Rongrong Ji , Liujuan Cao

Video understanding has made huge strides in recent years, relying largely on the power of transformers. As this architecture is notoriously expensive and video data is highly redundant, research into improving efficiency has become…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xinyue Hao , Gen Li , Shreyank N Gowda , Robert B Fisher , Jonathan Huang , Anurag Arnab , Laura Sevilla-Lara

Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we…

Our work tackles the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs). Despite the effectiveness of contrastive learning, the substantial computational resources…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Jinhong Lin , Cheng-En Wu , Yibing Wei , Pedro Morgado

Training competitive deep video models is an order of magnitude slower than training their counterpart image models. Slow training causes long research cycles, which hinders progress in video understanding research. Following standard…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Chao-Yuan Wu , Ross Girshick , Kaiming He , Christoph Feichtenhofer , Philipp Krähenbühl

In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Michael S. Ryoo , AJ Piergiovanni , Anurag Arnab , Mostafa Dehghani , Anelia Angelova

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Zihang Jiang , Qibin Hou , Li Yuan , Daquan Zhou , Yujun Shi , Xiaojie Jin , Anran Wang , Jiashi Feng

Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A key bottleneck stems…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Weili Zeng , Ziyuan Huang , Kaixiang Ji , Yichao Yan

Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Leqi Shen , Tianxiang Hao , Tao He , Sicheng Zhao , Yifeng Zhang , Pengzhang Liu , Yongjun Bao , Guiguang Ding