中文
相关论文

相关论文: SWIFT: Sliding Window Reconstruction for Few-Shot …

200 篇论文

Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthetic datasets do not faithfully recreate the data…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Jae Myung Kim , Stephan Alaniz , Cordelia Schmid , Zeynep Akata

Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Yanxiao Sun , Jiafu Wu , Yun Cao , Chengming Xu , Yabiao Wang , Weijian Cao , Donghao Luo , Chengjie Wang , Yanwei Fu

Detecting the source model of AI-generated images is a growing accountability problem. AI fingerprinting techniques address this by detecting imperceptible patterns in the images that are unique to each model, achieving high detection…

密码学与安全 · 计算机科学 2026-05-06 Kai Yao , Marc Juarez

Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumption: verification can succeed only if the diffusion trajectory…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Rui Bao , Zheng Gao , Xiaoyu Li , Xiaoyan Feng , Yang Song , Jiaojiao Jiang

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

计算与语言 · 计算机科学 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

Long interaction histories are central to modern recommender systems, yet training with long sequences is often dismissed as impractical under realistic memory and latency budgets. This work demonstrates that it is not only practical but…

机器学习 · 计算机科学 2026-04-15 Sayak Chakrabarty , Souradip Pal

Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to…

计算与语言 · 计算机科学 2025-03-07 Heming Xia , Yongqi Li , Jun Zhang , Cunxiao Du , Wenjie Li

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Jiaqi Xu , Kunzhe Huang , Xinyi Zou , Yunkuo Chen , Bo Liu , MengLi Cheng , Jun Huang , Xing Shi

Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles…

机器学习 · 计算机科学 2025-05-22 Nanxu Gong , Zijun Li , Sixun Dong , Haoyue Bai , Wangyang Ying , Xinyuan Wang , Yanjie Fu

Short video has witnessed rapid growth in the past few years in e-commerce platforms like Taobao. To ensure the freshness of the content, platforms need to release a large number of new videos every day, making conventional click-through…

信息检索 · 计算机科学 2022-09-14 Sihao Hu , Yi Cao , Yu Gong , Zhao Li , Yazheng Yang , Qingwen Liu , Shouling Ji

Recent advancements in diffusion models have revolutionized video generation, enabling the creation of high-quality, temporally consistent videos. However, generating high frame-rate (FPS) videos remains a significant challenge due to…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Geunmin Hwang , Hyun-kyu Ko , Younghyun Kim , Seungryong Lee , Eunbyung Park

Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a…

计算机视觉与模式识别 · 计算机科学 2021-04-06 Jia-Chang Feng , Fa-Ting Hong , Wei-Shi Zheng

Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Zening Sun , Zhengpeng Xie , Lichen Bai , Shitong Shao , Shuo Yang , Zeke Xie

Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since…

Photorealistic color retouching plays a vital role in visual content creation, yet manual retouching remains inaccessible to non-experts due to its reliance on specialized expertise. Reference-based methods offer a promising alternative by…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Melany Yang , Yuhang Yu , Diwang Weng , Jinwei Chen , Wei Dong

We introduce Mistake Attribution (MATT), a new task for fine-grained understanding of human mistakes in egocentric videos. While prior work detects whether a mistake occurs, MATT attributes the mistake to what part of the instruction is…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Yayuan Li , Aadit Jain , Filippos Bellos , Jason J. Corso

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Yunhong Lu , Yanhong Zeng , Haobo Li , Hao Ouyang , Qiuyu Wang , Ka Leong Cheng , Jiapeng Zhu , Hengyuan Cao , Zhipeng Zhang , Xing Zhu , Yujun Shen , Min Zhang

Text-to-image generative models have recently garnered significant attention due to their ability to generate images based on prompt descriptions. While these models have shown promising performance, concerns have been raised regarding the…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Meiling Li , Zhenxing Qian , Xinpeng Zhang

Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Jimin Tang , Wenyuan Zhang , Junsheng Zhou , Zian Huang , Kanle Shi , Shenkun Xu , Yu-Shen Liu , Zhizhong Han

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition…

计算机视觉与模式识别 · 计算机科学 2023-03-22 Wei Lin , Muhammad Jehanzeb Mirza , Mateusz Kozinski , Horst Possegger , Hilde Kuehne , Horst Bischof