Papers › Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval

Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval

15 Aug 2023ICCV 2023 1arXiv:2308.07648archive 2025-07-28

Chaorui Deng, Qi Chen, Pengda Qin, Da Chen, Qi Wu

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.07648")

Code

Syntology Ran 4 of 16 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bladewaltz1/promptswitch officialmentioned in paperpytorch 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

16 samples harvested; 4 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
3ran
12unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from bladewaltz1/promptswitch. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

CLIPEncoderLayer bladewaltz1/promptswitch/model/prompt_clip.py official repository ran fingerprinted no licence file found · pointer only · 6b5c6a4c5fe3629a · report
CLIPTextEmbeddings bladewaltz1/promptswitch/model/prompt_clip.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 7afff4a1c7789597 · report
CLIPVisionEmbeddings bladewaltz1/promptswitch/model/prompt_clip.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 97b7de8e8d588a6e · report
_expand_mask bladewaltz1/promptswitch/model/prompt_clip.py official repository ran · our draft was wrong no licence file found · pointer only · 749dd08d5d7409f2 · report
BaselinePooling bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 6b28b5c3f3f4e210 · report
CLIPAttention bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 4c0e317bbad36a96 · report
CLIPEncoder bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 4521a46931a2dd05 · report
CLIPEncoderLayerPT bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 072dd8bae2230fa6 · report
CLIPEncoderPT bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 01439931fe5d4f12 · report
CLIPModel bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 90804502b77c9f49 · report
CLIPTextTransformer bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · be95c1088bdc81ad · report
CLIPVisionTransformer bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 925873e2ceea0336 · report
Config bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · e28877d426856a6f · report
MultiHeadedAttention bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 90011c4f1d727ebe · report
PromptCLIP bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 87939011e0a0b2dd · report
Transformer bladewaltz1/promptswitch/model/prompt_clip.py official repository unverified no licence file found · pointer only · 3654adee70b77587 · report

Tasks

RetrievalVideo CaptioningVideo Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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