5 papers
From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification
Ke Zhang, Xiangchen Zhao, Yunjie Tian +3
Conventional video classification models, acting as effective imitators, excel in scenarios with homogeneous data distributions. However, real-world applications often present an o…
Few-Step Diffusion Sampling Through Instance-Aware Discretizations
Liangyu Yuan, Ruoyu Wang, Tong Zhao +4
Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Stochastic Differential Equations (ODEs/SDEs), starting from a tractable p…
Shot-Aware Frame Sampling for Video Understanding
Mengyu Zhao, Di Fu, Yongyu Xie +4
Video frame sampling is essential for efficient long-video understanding with Vision-Language Models (VLMs), since dense inputs are costly and often exceed context limits. Yet when…
CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization
Xiaoman Feng, Mingkun Lei, Yang Wang +2
Style transfer in diffusion models enables controllable visual generation by injecting the style of a reference image. However, recent encoder-based methods, while efficient and tu…
RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification
Meilong Xu, Di Fu, Jiaxing Zhang +7
Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particul…