Research map / Video / Video-language understanding
How Video Meetings Change Your Expression
Sumit Sarin, Utkarsh Mall, Purva Tendulkar, Carl Vondrick
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| predict translator parameters instead of retrieving from a fixed set of 32 (ablation) | FACET with variable chunks (c=2) · ZoomIn | discriminator accuracy (%): 92.26 -> 73.28 | Improved |
| learn variable change-point chunks instead of fixed-size chunks (ablation) | FACET (c=2) · ZoomIn | discriminator accuracy (%): 82.99 -> 73.28 | Improved |
| partition clip into 2 learned chunks instead of no partition (ablation) | FACET · ZoomIn | discriminator accuracy (%): 78.54 -> 73.28 | Improved |
| increase number of chunks from 2 to 7 (ablation) | FACET · ZoomIn | discriminator accuracy (%): 73.28 -> 73.16 | No clear effect |
| predict both shift and scale rather than scale only (ablation) | FACET translator · ZoomIn | discriminator accuracy (%): 86.50 -> 73.28 | Improved |
| predict both shift and scale rather than shift only (ablation) | FACET translator · Presidents | discriminator accuracy (%): 96.52 -> 79.35 | Improved |
| increase chunks from 2 to 7 for fixed-size chunks with predicted translator (ablation) | baseline · Presidents | discriminator accuracy (%): 88.67 -> 89.86 | Hurt |
Closest papers by meaning
- Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation (CVPR 2024 · similarity 0.85)
- GLARE: Generating Listening Heads with Appropriate REactions (NeurIPS 2026 · similarity 0.85)
- Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception (NeurIPS 2026 · similarity 0.85)
- Teaching Human Behavior Improves Content Understanding Abilities Of VLMs (ICLR 2025 · similarity 0.84)
- SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models (NeurIPS 2025 · similarity 0.84)
- VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
