CLIP2TV: An Empirical Study on Transformer-based Methods for Video-Text Retrieval

By Zijian Gao, Jingyun Liu, Sheng Chen, Dedan Chang, Hao Zhang, Jinwei Yuan. 2021

74 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

1. Krzysztof Marcin Choromanski
2. Vikas Sindhwani
3. Andy Zeng

In Multimodal Learning

1. Xiansheng Hua
2. Michael S. Ryoo
3. Andy Zeng

Citations in the corpus

• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, methodology): “…1.0 no ViT-V/32 DRL (Wang et al. 2022), ViT-B/32 45.3 73.9 83.3 2.0 no ViT-V/32 CAMoE (Cheng et al. 2021) 49.1 74.3 84.3 2.0 no ViT-B/32 CLIP2TV (Gao et al. 2021) 54.1 77.4 85.7 1.0 no ViT-B/16 DRL (Wang et al. 2022), ViT-B/16 + QB-n 56.2 79.9 87.4 1.0 no ViT-B/16 Zero-shot SSB (Patrick et al.…”
• Disentangled Representation Learning for Text-Video Retrieval (2022, background): “Researchers [34,2,29,11,13] explore the power of this design principle to text-video retrieval with additional temporal fusion module.”