English
Related papers

Related papers: PAS: A Training-Free Stabilizer for Temporal Encod…

200 papers

Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Youngrae Kim , Qixin Hu , C. -C. Jay Kuo , Peter A. Beerel

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Wentai Zhang , Ronghui Xi , Shiyao Peng , Jiayu Huang , Haoran Luo , Zichen Tang , Haihong E

Extending the context length of Language Models (LMs) by improving Rotary Position Embedding (RoPE) has become a trend. While prior works mainly address RoPE's limitations within attention, this paper uncovers the adverse effects on length…

Artificial Intelligence · Computer Science 2025-07-15 Ermo Hua , Che Jiang , Xingtai Lv , Kaiyan Zhang , Youbang Sun , Yuchen Fan , Xuekai Zhu , Biqing Qi , Ning Ding , Bowen Zhou

Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user supervision, for example, when sparse point prompts are provided on a single frame, their…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Dawar Jyoti Deka

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully…

Image and Video Processing · Electrical Eng. & Systems 2021-03-18 Ren Yang , Fabian Mentzer , Luc Van Gool , Radu Timofte

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…

Artificial Intelligence · Computer Science 2025-11-03 Zikang Liu , Longteng Guo , Yepeng Tang , Tongtian Yue , Junxian Cai , Kai Ma , Qingbin Liu , Xi Chen , Jing Liu

Positional encoding is essential for large language models (LLMs) to represent sequence order, yet recent studies show that Rotary Position Embedding (RoPE) can induce massive activation. We investigate the source of these instabilities via…

Computation and Language · Computer Science 2026-01-07 Jing Xiong , Liyang Fan , Hui Shen , Zunhai Su , Min Yang , Lingpeng Kong , Ngai Wong

Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Hao Zhang , Lechao Cheng , Yanbin Hao , Chong-Wah Ngo

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Yanbin Hao , Diansong Zhou , Zhicai Wang , Chong-Wah Ngo , Meng Wang

Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yigui Feng , Qinglin Wang , Yang Liu , Jie Liu

Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Zhangkai Wu , Xuhui Fan , Zhongyuan Xie , Kaize Shi , Longbing Cao

Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches is the difficulty of retaining essential visual and temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Leqi Shen , Tao He , Guoqiang Gong , Fan Yang , Yifeng Zhang , Pengzhang Liu , Sicheng Zhao , Guiguang Ding

When applied sequentially to video, frame-based networks often exhibit temporal inconsistency - for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Matthew Dutson , Nathan Labiosa , Yin Li , Mohit Gupta

Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Hidir Yesiltepe , Tuna Han Salih Meral , Adil Kaan Akan , Kaan Oktay , Pinar Yanardag

Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user…

Graphics · Computer Science 2026-04-24 Etai Sella , Yoav Baron , Hadar Averbuch-Elor , Daniel Cohen-Or , Or Patashnik

We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Sanjay Haresh , Sateesh Kumar , Huseyin Coskun , Shahram Najam Syed , Andrey Konin , Muhammad Zeeshan Zia , Quoc-Huy Tran

Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Hong Nguyen , Dung Tran , Hieu Hoang , Phong Nguyen , Shrikanth Narayanan

Existing frameworks for learned video compression suffer from a dilemma between inaccurate temporal alignment and error propagation for motion estimation and compensation (ME/MC). The separate-transform framework employs distinct transforms…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Han Li , Shaohui Li , Wenrui Dai , Chenglin Li , Xinlong Pan , Haipeng Wang , Junni Zou , Hongkai Xiong

Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window, primarily due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). Recent studies…

Computation and Language · Computer Science 2025-08-06 Sikui Zhang , Guangze Gao , Ziyun Gan , Chunfeng Yuan , Zefeng Lin , Houwen Peng , Bing Li , Weiming Hu
‹ Prev 1 2 3 10 Next ›