论文解读
当 AI 自己给艺术分类：28 个簇与 6 个人类标签的错位
音视频理解 | 4.0/10
音视频理解
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
论文解读
不训练模型，只靠对齐：用图像把英文单词钉到印地语语音里
音频检索 | 7.3/10
论文解读
Omni 不等于会选：当模型被要求用对的模态回答
音视频理解 | 7.8/10
论文解读
不只用文字指挥检索：当嵌入器学会看区域、听时段
音频检索 | 7.5/10
论文解读
别再把同步分数当裁判：先问它量的是偏移、内容，还是感知代理
音视频理解 | 8.8/10
论文解读
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
音视频理解 | 9.4/10
论文解读
Task-disentangled Low-Rank Adaptation for Versatile Audio-visual Multi-modal Learning Tasks within a Unified Framework
音视频理解 | 7.4/10
论文解读
Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026
音视频理解 | 7.1/10
论文解读
Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video
音视频理解 | 9.0/10
论文解读
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
音视频理解 | 10.0/10
论文解读
Towards Actionable Surgical Team Dynamics: from Teamwork to Counterfactual Annotations
音视频理解 | 8.9/10
论文解读
DAVSS: Distilled Audio-Visual State Space Models
音视频理解 | 6.4/10
论文解读
Multimodal Rapport Estimation in Real-World HRI
多模态模型 | 7.0/10
论文解读
Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models
音视频理解 | 7.4/10
论文解读
On computational approaches to Pop music culture
音乐理解 | 6.1/10
论文解读
CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection
音视频理解 | 7.2/10
论文解读
Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis
音视频理解 | 6.5/10
论文解读
Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety
音视频理解 | 4.4/10
论文解读
AI-Guided Learning: Research on Knowledge and Skill Acquisition Support Methods Using Deep Learning Audio-Video Processing Techniques
音视频理解 | 6.3/10
论文解读
AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward
音频字幕生成 | 8.4/10