English
Related papers

Related papers: Dynamic Token Compression for Efficient Video Unde…

200 papers

Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Yadong Qu , Yuxin Wang , Bangbang Zhou , Zixiao Wang , Hongtao Xie , Yongdong Zhang

Neural data compression has been shown to outperform classical methods in terms of $RD$ performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input…

Machine Learning · Computer Science 2021-06-02 Ties van Rozendaal , Iris A. M. Huijben , Taco S. Cohen

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…

Artificial Intelligence · Computer Science 2026-05-08 Zijun Gao , Zhikun Xu , Xiao Ye , Ben Zhou

One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for…

Image and Video Processing · Electrical Eng. & Systems 2020-04-22 Nannan Zou , Honglei Zhang , Francesco Cricri , Hamed R. Tavakoli , Jani Lainema , Emre Aksu , Miska Hannuksela , Esa Rahtu

Most existing video summarisation methods are based on either supervised or unsupervised learning. In this paper, we propose a reinforcement learning-based weakly supervised method that exploits easy-to-obtain, video-level category labels…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Kaiyang Zhou , Tao Xiang , Andrea Cavallaro

Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Joonmyung Choi , Sanghyeok Lee , Jongha Kim , Sehyung Kim , Dohwan Ko , Jihyung Kil , Hyunwoo J. Kim

We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Jathushan Rajasegaran , Ilija Radosavovic , Rahul Ravishankar , Yossi Gandelsman , Christoph Feichtenhofer , Jitendra Malik

Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Sai Vemprala , Sami Mian , Ashish Kapoor

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

Image and Video Processing · Electrical Eng. & Systems 2024-10-28 Ruihan Yang , Yibo Yang , Joseph Marino , Stephan Mandt

Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which primarily based on training embeddings, face various challenges associated…

Computation and Language · Computer Science 2024-06-04 Hoyoun Jung , Kyung-Joong Kim

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Chao-Yuan Wu , Manzil Zaheer , Hexiang Hu , R. Manmatha , Alexander J. Smola , Philipp Krähenbühl

Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Li Haopeng , Ke Qiuhong , Gong Mingming , Tom Drummond

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in…

Computer Vision and Pattern Recognition · Computer Science 2020-10-21 Jongwon Choi , Hyung Jin Chang , Tobias Fischer , Sangdoo Yun , Kyuewang Lee , Jiyeoup Jeong , Yiannis Demiris , Jin Young Choi

Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Wang Lin , Liyu Jia , Wentao Hu , Kaihang Pan , Zhongqi Yue , Wei Zhao , Jingyuan Chen , Fei Wu , Hanwang Zhang

Most of the existing neural video compression methods adopt the predictive coding framework, which first generates the predicted frame and then encodes its residue with the current frame. However, as for compression ratio, predictive coding…

Image and Video Processing · Electrical Eng. & Systems 2021-12-15 Jiahao Li , Bin Li , Yan Lu

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

Autoregressive sequence models, such as Transformer-based vision-language action (VLA) policies, can be tremendously effective for capturing complex and generalizable robotic behaviors. However, such models require us to choose a…

The challenge in LLM-based video understanding lies in preserving visual and semantic information in long videos while maintaining a memory-affordable token count. However, redundancy and correspondence in videos have hindered the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Yudong Han , Qingpei Guo , Liyuan Pan , Liu Liu , Yu Guan , Ming Yang

Abstractive compression utilizes smaller langauge models to condense query-relevant context, reducing computational costs in retrieval-augmented generation (RAG). However, retrieved documents often include information that is either…

Computation and Language · Computer Science 2025-12-11 Singon Kim

Significant advances in video compression system have been made in the past several decades to satisfy the nearly exponential growth of Internet-scale video traffic. From the application perspective, we have identified three major…

Image and Video Processing · Electrical Eng. & Systems 2021-01-19 Dandan Ding , Zhan Ma , Di Chen , Qingshuang Chen , Zoe Liu , Fengqing Zhu