SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.10300 · ICLR · 2025

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Lina Yao, Xiaojun Chang, Heng Wang, Linjie Yang, Mingfei Han, Reler Lab

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
bytedance/Shot2Story canonical 6 of 7
FunctionStatusWhere it lives
generate_caption Ran bytedance/Shot2Story/code/app/caption.py
pointer only (licence: NONE) · get_code("56f02812d66a0d11")
get_concat_v Ran bytedance/Shot2Story/code/app/dataset_browser.py
pointer only (licence: NONE) · get_code("92f2e16ee0d3a24d")
read_img Ran bytedance/Shot2Story/code/app/calculate_coco_features.py
pointer only (licence: NONE) · get_code("13a43a7d815937e6")
resize_img Ran bytedance/Shot2Story/code/app/utils.py
pointer only (licence: NONE) · get_code("926bb38f979a61ef")
resize_img_w Ran bytedance/Shot2Story/code/app/dataset_browser.py
pointer only (licence: NONE) · get_code("f809f2ecf34c1c99")
sample_dataset Ran bytedance/Shot2Story/code/app/dataset_browser.py
pointer only (licence: NONE) · get_code("3d4bbb5ca53fd24a")
compute_gradcam_batch Not yet run bytedance/Shot2Story/code/app/multimodal_search.py
pointer only (licence: NONE) · get_code("3e12ea8c09674aa8")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 multishot video understanding benchmark Shot2Story with detailed shot-level captions, comprehensive video summaries and question-answering pairs. 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 captioning, multi-shot video summarization, and multi-shot video question answering. Preliminary experiments show some challenges to generate a long and comprehensive video summary for multi-shot videos. Nevertheless, the generated imperfect summaries can already achieve competitive performance on existing video understanding tasks such as video question-answering, promoting an underexplored setting of video understanding with detailed summaries.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2312.10300")
get_code_for_paper("2312.10300")
have("2312.10300")

Connect an agent — have() is free.