论文解读
CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering
多模态问答 | 6.6/10
视频理解
论文解读
OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
视频理解 | 7.3/10
论文解读
ViMU: Benchmarking Video Metaphorical Understanding
基准测试 | 8.1/10
每日研究速递
语音/音乐/音频论文速递 2026-05-17
共分析 2 篇语音/AI 论文
论文解读
VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Video
基准测试 | 7.0/10
论文解读
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
音频问答 | 7.0/10
会议任务专题
ICASSP 2026 - 视频理解
共 1 篇 ICASSP 2026 视频理解 方向论文
论文解读
Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing
音视频 | 7.0/10