Papers › Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

16 Dec 2023arXiv:2312.10300archive 2025-07-28

Mingfei Han, Linjie Yang, Xiaojun Chang, Heng Wang

A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark Shot2Story20K with detailed shot-level captions and comprehensive video summaries. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video and narration captioning, multi-shot video summarization, and video retrieval with shot descriptions. Preliminary experiments show some challenges to generate a long and comprehensive video summary. Nevertheless, the generated imperfect summaries can already significantly boost the performance of existing video understanding tasks such as video question-answering, promoting an under-explored setting of video understanding with detailed summaries.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2312.10300")

Code

Syntology Ran 6 of 7 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bytedance/Shot2Story officialmentioned 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

7 samples harvested; 6 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

6ran
1unverified

Licence: 7 of the 7 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 bytedance/Shot2Story. “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.

generate_caption bytedance/Shot2Story/code/app/caption.py official repository ran no licence file found · pointer only · 56f02812d66a0d11 · report
get_concat_v bytedance/Shot2Story/code/app/dataset_browser.py official repository ran no licence file found · pointer only · 92f2e16ee0d3a24d · report
read_img bytedance/Shot2Story/code/app/calculate_coco_features.py official repository ran no licence file found · pointer only · 13a43a7d815937e6 · report
resize_img bytedance/Shot2Story/code/app/utils.py official repository ran no licence file found · pointer only · 926bb38f979a61ef · report
resize_img_w bytedance/Shot2Story/code/app/dataset_browser.py official repository ran no licence file found · pointer only · f809f2ecf34c1c99 · report
sample_dataset bytedance/Shot2Story/code/app/dataset_browser.py official repository ran no licence file found · pointer only · 3d4bbb5ca53fd24a · report
compute_gradcam_batch bytedance/Shot2Story/code/app/multimodal_search.py official repository unverified no licence file found · pointer only · 3e12ea8c09674aa8 · report

Tasks

Video CaptioningVideo Question AnsweringVideo RetrievalVideo SummarizationVideo UnderstandingZero-Shot Video Question Answervideo narration captioning

Datasets

Introduced by this paper, per the archive.

Shot2Story20K

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Captioning Shot2Story20K Shot2Story BLEU-4 10.7 #2 of 2 Archive leaderboard report
Video Captioning Shot2Story20K Shot2Story CIDEr 37.4 #2 of 2 Archive leaderboard report
Video Captioning Shot2Story20K Shot2Story METEOR 16.2 #2 of 2 Archive leaderboard report
Video Captioning Shot2Story20K Shot2Story ROUGE 29.6 #2 of 2 Archive leaderboard report
Video Summarization Shot2Story20K SUM-shot BLEU-4 11.7 #2 of 2 Archive leaderboard report
Video Summarization Shot2Story20K SUM-shot CIDEr 8.6 #2 of 2 Archive leaderboard report
Video Summarization Shot2Story20K SUM-shot METEOR 19.7 #2 of 2 Archive leaderboard report
Video Summarization Shot2Story20K SUM-shot ROUGE 26.8 #2 of 2 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA SUM-shot+Vicuna Accuracy 56.8 #20 of 30 Archive leaderboard report
video narration captioning Shot2Story20K Ours BLEU-4 18.8 #1 of 1 Archive leaderboard report
video narration captioning Shot2Story20K Ours CIDEr 168.7 #1 of 1 Archive leaderboard report
video narration captioning Shot2Story20K Ours METEOR 24.8 #1 of 1 Archive leaderboard report
video narration captioning Shot2Story20K Ours ROUGE 39 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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