AI Paper Atlas

Research map / Point clouds / Point cloud classification

CL4D: Contrastive Language–4D Pretraining for Vision-Language Reasoning in Dynamic Scenes

Kumal Hewagamage, Isuranga Senavirathne, Sasika Amarasinghe, Hasitha Gallella, Dulanga Weerakoon, Vigneshwaran Subbaraju, Ranga Rodrigo

ECCV 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 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
use CL4D contrastive 4D encoder instead of P4Transformercontrastive text-motion alignment · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 53.57 -> 70.32Improved
use CL4D instead of Motion PointNetcontrastive text-motion alignment · DynAction4D ObjInteractionsText-to-motion R@1 (Batch): 41.37 -> 49.40Improved
use CL4D instead of Motion PointNetcontrastive text-motion alignment · DynAction4D ClutteredText-to-motion R@1 (Batch): 41.71 -> 55.07Improved
train the text encoder jointly instead of freezing it (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 56.63 -> 68.43Improved
use InfoNCE loss instead of SigLIP loss (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 66.97 -> 68.43Improved
initialize temporal encoder from pretrained 2D ViT (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 63.32 -> 68.43Improved
keep the correct temporal frame order instead of shuffling (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 60.97 -> 68.43Improved
change ViT backbone size (Tiny, Small, Base, Large) (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 68.79 / 69.61 / 68.43 / 66.95Mixed
use CL4D-mini (reduced spatial encoder, ViT-Tiny) (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 68.43 -> 67.18No clear effect
apply partial point clouds or random reconstruction error (ablation)CL4D-mini · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 67.18 -> 66.81 (partial), 65.85 (random error)No clear effect
increase training batch size from 16 to 72 (ablation)CL4D (InfoNCE) · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 58.71 -> 70.32Improved
increase number of input frames from 4 to 32 (ablation)CL4D · DynAction4D HumanOnlyText-to-motion R@1 (Batch): 49.85 -> 65.62Improved

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