论文解读
MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection
音视频理解 | 6.6/10
音视频理解
论文解读
SAMOT: State-Aware Step Modulation and Optimal Transport Matching for Audio-Visual Instance Segmentation
音视频理解 | 7.7/10
论文解读
SCoPE: Training-Free Audio-Visual Event Perception via Sparse Cross-Modal Prior Exchange
音视频理解 | 7.1/10
论文解读
C^2MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning
音视频理解 | 4.1/10
论文解读
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
音视频理解 | 7.7/10
论文解读
Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition
音视频理解 | 6.4/10
论文解读
Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
音视频理解 | 6.2/10
论文解读
AcoustiTrace: When Plausible Sound Violates Physics
音视频生成 | 6.9/10
论文解读
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs
音视频理解 | 8.1/10
论文解读
FATE: Frame-Level Audio-Visual Temporal Embedding
音视频理解 | 8.3/10
论文解读
FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models
音视频理解 | 7.9/10
论文解读
ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine
音视频理解 | 8.3/10
论文解读
CARE: A Multimodal Corpus for Studying Speech and Non-Verbal Communication Across Multiple Medical Conditions
音视频理解 | 7.9/10
论文解读
DynaBridge: Dynamic Summary-Guided Cross-Task Multimodal Fusion for DASS-Structured Mental Health Assessment
音视频理解 | 4.9/10
论文解读
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
音视频问答 | 7.0/10
论文解读
Towards High-Level Semantic Intelligence
音视频理解 | 7.0/10
论文解读
OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
音视频理解 | 6.9/10
论文解读
Efficient Audio-Visual Event Recognition via Knowledge Distillation and Dynamic INT8 Quantization of a Hybrid Cross-Attention Network
音视频理解 | 5.8/10
论文解读
EII-SCL: Harnessing Emotional Inertia for Multimodal Emotion Recognition in Conversation
语音情感识别 | 5.2/10
论文解读
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
音视频理解 | 6.0/10