AI Paper Atlas

Research map / Video / Video segmentation and tracking

Seeing without Pixels: Perception from Camera Trajectories

Zihui Xue, Kristen Grauman, Dima Damen, Andrew Zisserman, Tengda Han

CVPR 2026 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 3 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
use relative pose sequences instead of absolute (3D+4D) (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 34.74 -> 43.66Improved
use midpoint reference frame instead of previous pose (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 43.66 -> 44.02Improved
use 6D rotation instead of 4D quaternion (absolute) (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 34.74 -> 37.82Improved
use 6D rotation instead of 4D quaternion (relative midpoint) (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 44.02 -> 44.12No clear effect
add gravity direction input (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 44.12 -> 44.81Improved
add rotation to absolute translation (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 32.84 -> 37.82Improved
use Aria poses instead of video-estimated pi3 poses (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 43.86 -> 44.81No clear effect
finetune the text encoder instead of freezing (ablation)CamFormer · Ego-Exo4D text retrievaltop-1 accuracy (%): 44.81 -> 45.42Improved
add CamFormer pretraining (ablation)CamFormer · Ego-Exo4D proficiency (bouldering)accuracy (%): 63.52 -> 65.41Improved
add CamFormer pretraining (ablation)CamFormer · Ego-Exo4D activity classification (Aria poses)accuracy (%): 61.83 -> 71.28Improved
add CamFormer pretraining (ablation)CamFormer · UCF101-Dynamic (ViPE poses)accuracy (%): 64.18 -> 68.16Improved
fuse trajectory features with video featuresEgoVLPv2 · Ego-Exo4D keystep recognitionaccuracy (%): 29.17 -> 32.37Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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