pith. sign in

Msr-vtt: A large video description dataset for bridging video and language

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

VeRVE: Versatile Retrieval for Videos via Unified Embeddings

cs.CV · 2026-01-17 · unverdicted · novelty 7.0

VeRVE uses a shared MLLM backbone with contrastive alignment and LoRA training to surpass other MLLM methods on zero-shot video retrieval while enabling competitive moment retrieval and state-of-the-art composed retrieval without further training.

citing papers explorer

Showing 1 of 1 citing paper.

  • VeRVE: Versatile Retrieval for Videos via Unified Embeddings cs.CV · 2026-01-17 · unverdicted · none · ref 47

    VeRVE uses a shared MLLM backbone with contrastive alignment and LoRA training to surpass other MLLM methods on zero-shot video retrieval while enabling competitive moment retrieval and state-of-the-art composed retrieval without further training.