AI Paper Atlas

Research map / Video / Video-language understanding

Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos

Dhruv Verma, Debaditya Roy, Basura Fernando

IJCV 2025 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 5 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
replace CoFormer with ClipSitu XTF using CLIP embeddingsimSitu test, top-1 predicted verb · imSituvalue: 35.98 -> 47.21Improved
use ClipSitu Verb MLP instead of linear probe on CLIPViT-L14@336px verb prediction · imSituverb top-1: 53.4 -> 57.9Improved
use ClipSitu Verb MLP instead of fine-tuning CLIP with wise-ftViT-L14@336px verb prediction · imSituverb top-1: 52.2 -> 57.9Improved
use 2 hidden layers instead of 1 in Verb MLP (ablation)ClipSitu Verb MLP, ViT-L14@336px · imSituverb top-1: 57.9 -> 56.2Hurt
use 3 hidden layers instead of 1 in Verb MLP (ablation)ClipSitu Verb MLP, ViT-L14@336px · imSituverb top-1: 57.9 -> 54.3Hurt
use minimum annotator cross-entropy loss instead of per-annotator cross-entropy (ablation)ClipSitu MLP · imSituvalue: 76.57 -> 76.91Improved
use CLIP embeddings instead of ALIGN (ablation)ClipSitu XTF · imSitu devvalue (top-1 verb): 31.17 -> 47.23Improved
use CLIP text embeddings instead of Glove for verbs and roles (ablation)ClipSitu XTF · imSitu devvalue (top-1 verb): 42.40 -> 47.23Improved
increase patch tokens via larger encoder ViT-L14@336px instead of ViT-B32 (ablation)ClipSitu XTF · imSitu ground-truth verbvalue: 75.2 -> 78.5Improved
add cross-attention scores to verb-role embeddings for noun localization (ablation)ClipSitu XTF · imSitu ground-truth verbgrounded value: 27.81 -> 55.36Improved
use cross-attention scores from first layer instead of last layer (ablation)ClipSitu XTF · imSitu top-1 verbgrounded value: 33.30 -> 39.30Improved
use XTF encoder instead of MLP with decoder on video (ablation)ClipSitu+TxD, X-CLIP ViT-L14 · VidSituCIDEr: 61.93 -> 49.65Hurt

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