English
Related papers

Related papers: Video, How Do Your Tokens Merge?

200 papers

In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Bowen Zhang , Jiahui Yu , Christopher Fifty , Wei Han , Andrew M. Dai , Ruoming Pang , Fei Sha

Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet…

Computer Vision and Pattern Recognition · Computer Science 2016-09-27 Christoph Feichtenhofer , Axel Pinz , Andrew Zisserman

Video transition effects are widely used in video editing to connect shots for creating cohesive and visually appealing videos. However, it is challenging for non-professionals to choose best transitions due to the lack of cinematographic…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Yaojie Shen , Libo Zhang , Kai Xu , Xiaojie Jin

Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training and assign them with a mixed label with the same ratio.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Han Xiao , Wenzhao Zheng , Zheng Zhu , Jie Zhou , Jiwen Lu

This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokenize videos through a naive frame-sampling strategy, we…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Feng Wang , Yichun Shi , Ceyuan Yang , Qiushan Guo , Jingxiang Sun , Alan Yuille , Peng Wang

Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Shuhuai Ren , Sishuo Chen , Shicheng Li , Xu Sun , Lu Hou

Can we train a single transformer model capable of processing multiple modalities and datasets, whilst sharing almost all of its learnable parameters? We present PolyViT, a model trained on image, audio and video which answers this…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Valerii Likhosherstov , Anurag Arnab , Krzysztof Choromanski , Mario Lucic , Yi Tay , Adrian Weller , Mostafa Dehghani

Multi-task model merging offers a promising paradigm for integrating multiple expert models into a unified model without additional training. Existing state-of-the-art techniques, such as Task Arithmetic and its variants, merge models by…

Artificial Intelligence · Computer Science 2025-05-15 Wenju Sun , Qingyong Li , Yangli-ao Geng , Boyang Li

Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Yuzhang Shang , Mu Cai , Bingxin Xu , Yong Jae Lee , Yan Yan

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video$+$question, video$+$speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal…

Computer Vision and Pattern Recognition · Computer Science 2023-04-12 Xudong Lin , Simran Tiwari , Shiyuan Huang , Manling Li , Mike Zheng Shou , Heng Ji , Shih-Fu Chang

Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a token. Generally, representing an image with more tokens…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yulin Wang , Rui Huang , Shiji Song , Zeyi Huang , Gao Huang

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Taekyung Kim , Byeongho Heo , Dongyoon Han

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

In recent years, many video tasks have achieved breakthroughs by utilizing the vision transformer and establishing spatial-temporal decoupling for feature extraction. Although multi-view 3D reconstruction also faces multiple images as…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Zhenwei Zhu , Liying Yang , Ning Li , Chaohao Jiang , Yanyan Liang

Vision transformers have achieved great successes in many computer vision tasks. Most methods generate vision tokens by splitting an image into a regular and fixed grid and treating each cell as a token. However, not all regions are equally…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 Wang Zeng , Sheng Jin , Wentao Liu , Chen Qian , Ping Luo , Wanli Ouyang , Xiaogang Wang

Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image. These cross-modal interactions are computationally expensive and memory-intensive due to the quadratic complexity…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Qingqing Cao , Bhargavi Paranjape , Hannaneh Hajishirzi

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

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

Despite the prosperity of the video language model, the current pursuit of comprehensive video reasoning is thwarted by the inherent spatio-temporal incompleteness within individual videos, resulting in hallucinations and inaccuracies. A…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Zhihao He , Tianyao He , Yun Xu , Tieyuan Chen , Huabin Liu , Chaofan Gan , Zuxuan Wu , Weiyao Lin

Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures…

Computer Vision and Pattern Recognition · Computer Science 2024-01-11 Qian Wu , Ruoxuan Cui , Yuke Li , Haoqi Zhu