AI Paper Atlas

Research map / Video / Video-language understanding

Open Vocabulary Multi-Label Video Classification

Rohit Gupta, Mamshad Nayeem Rizve, Jayakrishnan Unnikrishnan, Ashish Tawari, Son Tran, Mubarak Shah, Benjamin Yao, Trishul A Chilimbi

ECCV 2024 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 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
replace fixed LLM prompts with learnable LLM prompts and prompt transformer (ablation)CLIP label encoder · ActivityNet (open vocab)AUPR: 48.1 -> 50.2Improved
add prompt transformer to the fixed-prompt LLM label encoder (ablation)CLIP label encoder · ActivityNet (open vocab)AUPR: 41.3 -> 48.1Improved
add an LLM to the CLIP text encoder label encoder (ablation)label encoder · ActivityNet (open vocab)AUPR: 34.5 -> 50.2Improved
keep the CLIP text encoder in the label encoder (ablation)label encoder · TAO (open vocab)AUPR: 25.2 -> 65.5Improved
add parallel temporal modeling branchCLIP + Learnable LLM Prompts · TAO (open vocab)AUPR: 51.4 -> 63.8Improved
add temporal modelingCLIP + Learnable LLM Prompts · ActivityNet (open vocab)AUPR: 47.1 -> 47.1No clear effect
add stochastic weight regularization on temporal-branch spatial layers (ablation)temporal modeling branch · ActivityNet (open vocab)Peak F1: 32.5 -> 53.8Improved
unfreeze the CLIP vision backbone (no regularization) (ablation)temporal modeling branch · TAO (open vocab)Peak F1: 62.1 -> 42.7Hurt
use more temporal blocks up to 4 (ablation)temporal modeling branch · ActivityNet (open vocab)AUPR: 47.7 (1 block) -> 50.2 (4) -> 48.1 (5)Mixed
use parallel instead of serial temporal blocks (ablation)temporal modeling branch · ActivityNet (open vocab)Peak F1: 41.5 -> 52.6Improved
add synthetic labels from a multimodal LLM to training datafull method · ActivityNet (open vocab)AUPR: 47.1 -> 50.2Improved
add synthetic labelsfull method · TAO (open vocab)Peak F1: 59.6 -> 56.6Hurt

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