paper-with-me

Papers

Learning Conditional Space-Time Prompt Distributions for Video Class-Incremental Learning

2025-01-01 · CVPR 2025 1 · Xiaohan Zou, Wenchao Ma, Shu Zhao

Recent advancements in prompt-based learning have significantly advanced image and video class-incremental learning. However, the prompts learned by these methods often fail to capture the diverse and informative characteristics of videos, and struggle to generalize effectively to future tasks and classes. To address these challenges, this paper proposes modeling the distribution of space-time prompts conditioned on the input video using a diffusion model. This generative approach allows the proposed model to naturally handle the diverse characteristics of videos, leading to more robust prompt learning and enhanced generalization capabilities. Additionally, we develop a simple yet effective mechanism to transfer the token relationship modeling capabilities of pre-trained image transformers to spatio-temporal modeling in videos. Our approach has been thoroughly evaluated across four established benchmarks, showing remarkable improvements over existing state-of-the-art methods in video class-incremental learning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningClass Incremental LearningIncremental LearningPrompt Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors

2026-03-19 · Yusuke Takase, Momose Oyama, Hidetoshi Shimodaira arxiv

We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing their conditional distributions. In this space, distances between models ap…

Learning Long-term Motion Embeddings for Efficient Kinematics Generation

2026-04-13 · Nick Stracke, Kolja Bauer, Stefan Andreas Baumann, Miguel Angel Bautista 외 arxiv

Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video s…

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

2025-10-16 · Meiqi Wu, Jiashu Zhu, Xiaokun Feng, Chubin Chen 외 arxiv

Video generation models have achieved remarkable progress, particularly excelling in realistic scenarios; however, their performance degrades notably in imaginative scenarios. These prompts often involve rarely co-occurr…

Video Generation

TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation

2024-06-12 · Weixi Feng, Jiachen Li, Michael Saxon, Tsu-Jui Fu 외

Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this …

BenchmarkingImage GenerationImage to Video GenerationVideo Generation

Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models

2025-07-11 · Shijun Yang, Xiang Zhang, Wanqing Zhao, Hangzai Luo 외 arxiv

Prompt learning facilitates the efficient adaptation of Vision-Language Models (VLMs) to various downstream tasks. However, it faces two significant challenges: (1) inadequate modeling of class embedding distributions fo…