Papers › Zero-Shot Video Captioning with Evolving Pseudo-Tokens

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

22 Jul 2022arXiv:2207.11100archive 2025-07-28

Yoad Tewel, Yoav Shalev, Roy Nadler, Idan Schwartz, Lior Wolf

We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Unlike zero-shot image captioning methods, our work considers the entire sentence at once. This is achieved by optimizing, during the generation process, part of the prompt from scratch, by modifying the representation of all other tokens in the prompt, and by repeating the process iteratively, gradually improving the specificity and comprehensiveness of the generated sentence. Our experiments show that the generated captions are coherent and display a broad range of real-world knowledge. Our code is available at: https://github.com/YoadTew/zero-shot-video-to-text

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yoadtew/zero-shot-video-to-text officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CaptioningImage-text matchingLanguage ModelingLanguage ModellingSentenceSpecificityText MatchingVideo CaptioningWorld Knowledge

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECLIPCosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections