EmoTrace-Bench: Diagnosing Emotional Expression in Text-to-Video Generation through Controlled Cues and Intensity

cs.CV

Submitted: 2026-10-11

Updated: 2026-10-11

Comments: 30 pages. Code and data: https://github.com/Tonyheng6/EmoTrace-Bench

Code: https://github.com/Tonyheng6/EmoTrace-Bench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
• EmoWorld: A Decoupled Affective Field for Controllable Emotional Video Generation
• FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
• VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models