AI Paper Atlas

Research map / Video / Video generation

Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos

Xavier Thomas, Youngsun Lim, Ananya Srinivasan, Audrey Zheng, Deepti Ghadiyaram

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add supervised contrastive loss (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.26 -> 0.61Improved
add supervised contrastive loss (ablation)action manifold encoder · TAG-Bench-v0 Temporal CoherenceSpearman correlation: 0.38 -> 0.64Improved
add hard-negative temporal distortion loss (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.54 -> 0.61Improved
add hard-negative temporal distortion loss (ablation)action manifold encoder · TAG-Bench-v0 Temporal CoherenceSpearman correlation: 0.57 -> 0.64Improved
add motion (temporal derivative) features (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.46 -> 0.61Improved
add 3D pose features (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.56 -> 0.61Improved
add 2D keypoint features (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.61 -> 0.61No clear effect
use ViT (TokenHMR) visual features instead of CLIP (ablation)action manifold encoder · TAG-Bench-v0 Temporal CoherenceSpearman correlation: 0.39 -> 0.64Improved
add human-centric 3D/2D features to CLIP-only input (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.12 -> 0.51Improved
increase temporal window from 4 to 32 frames (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.39 -> 0.61Improved
increase temporal window beyond 32 frames (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.61 -> 0.56No clear effect
use attention-weighted per-frame fusion instead of no fusion (ablation)action manifold encoder · TAG-Bench-v0 Action ConsistencySpearman correlation: 0.53 -> 0.61Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy