Papers with VTT

6 papers
Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks (2023.findings-eacl)

Copied to clipboard

Challenge: Existing benchmarks for text-to-video retrieval are incomplete, resulting in false negatives . a recent state-of-the-art model gains 25% recall points, but this is not the case for TVR.
Approach: They propose to retire video captioning datasets as TVR benchmarks . they propose to annotate and release additional caption-video pairs to mitigate this flaw .
Outcome: The proposed method fails to accurately reflect reality, despite lack of purpose-built benchmarks.
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for video captioning consider a sequence of frames and biases towards focused objects.
Approach: They propose an Object-Oriented Non-Autoregressive approach to video captioning . it performs three steps: 1) identify the focused objects and predict their locations . 2) generate related attribute words and relation words of these focused objects to form a draft caption .
Outcome: The proposed method achieves competitive results with the state-of-the-art methods but with higher diversity and faster inference speed.
MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline (2024.emnlp-industry)

Copied to clipboard

Challenge: Recent advances in text-video retrieval neglect the crucial user perspective, leading to discrepancies between user queries and content retrieved.
Approach: They propose a novel, training-free pipeline that leverages Large Language Models for iterative feedback learning.
Outcome: Experimental results show that MERLIN significantly outperforms existing systems in video retrieval.
Semi-Supervised Learning for Video Captioning (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing video captioning algorithms are heavily dependent on supervised training data.
Approach: They propose to train the video captioning model on labeled and unlabeled data jointly in a semi-supervised learning manner.
Outcome: The proposed model outperforms state-of-the-art semi-supervised learning approaches on VATEX, MSR-VTT and MSVD datasets.
Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models (2021.naacl-main)

Copied to clipboard

Challenge: a new study examines zero-shot cross-lingual transfer of vision-language models . we study multilingual text-to-video search in non-English languages without annotations .
Approach: They propose a Transformer-based model that learns contextual multilingual multimodal embeddings . they propose 'zero-shot cross-lingual transfer' to improve multilingual search .
Outcome: The proposed model outperforms baselines on multilingual text-to-video search and multilingual image search on VTT and VATEX.
MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for video retrieval rely on embedding-based full-corpus scanning, but there is a bottleneck in semantic asymmetry and computational redundancy.
Approach: They propose a multi-agent framework that rethinks retrieval as cooperative reasoning . they parse raw videos into a structured semantic library, enabling explicit attribute-level indexing .
Outcome: The proposed framework bridges the granularity mismatch gap by parsing raw videos into a structured semantic library . it employs a Logic-aware Debate mechanism with a strict veto protocol . the proposed framework achieves competitive performance without task-specific fine-tuning .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations