Papers › HourVideo: 1-Hour Video-Language Understanding

HourVideo: 1-Hour Video-Language Understanding

7 Nov 2024arXiv:2411.04998archive 2025-07-28

Keshigeyan Chandrasegaran, Agrim Gupta, Lea M. Hadzic, Taran Kota, Jimming He, Cristóbal Eyzaguirre, Zane Durante, Manling Li, Jiajun Wu, Li Fei-Fei

We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve marginal improvements over random chance. In stark contrast, human experts significantly outperform the state-of-the-art long-context multimodal model, Gemini Pro 1.5 (85.0% vs. 37.3%), highlighting a substantial gap in multimodal capabilities. Our benchmark, evaluation toolkit, prompts, and documentation are available at https://hourvideo.stanford.edu

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="2411.04998")

Code

Syntology Ran 1 of 16 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

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

keshik6/HourVideo officialmentioned on GitHubApache-2.0 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; 1 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
15unverified

Licence: 0 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 keshik6/HourVideo. “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.

encode_image keshik6/HourVideo/hourvideo/gpt4_utils.py official repository ran · our draft was wrong Apache-2.0 (permissive) · f41cb1a19b154297 · report
check_caption_completion_status keshik6/HourVideo/hourvideo/form_world_state_history.py official repository unverified Apache-2.0 (permissive) · d31b2cfa1a2eabc8 · report
convert_seconds_to_hms keshik6/HourVideo/hourvideo/llm_utils.py official repository unverified Apache-2.0 (permissive) · aca03fd411a5b059 · report
correct_keys_in_list keshik6/HourVideo/hourvideo/gpt4_utils.py official repository unverified Apache-2.0 (permissive) · 8c8de8a6584771d2 · report
create_index_lists keshik6/HourVideo/hourvideo/gpt4_captioner.py official repository unverified Apache-2.0 (permissive) · e06becb29bf68207 · report
extract_first_letter keshik6/HourVideo/hourvideo/gemini_utils.py official repository unverified Apache-2.0 (permissive) · 1a60d839f3eb71b4 · report
filter_intervals keshik6/HourVideo/hourvideo/form_world_state_history.py official repository unverified Apache-2.0 (permissive) · 65d9bfa83974ba96 · report
get_color keshik6/HourVideo/hourvideo/hv_utils.py official repository unverified Apache-2.0 (permissive) · 132f9da86c87ad0d · report
get_openai_completion keshik6/HourVideo/hourvideo/gpt4_captioner.py official repository unverified Apache-2.0 (permissive) · d37eb61fd6663794 · report
get_world_state_history keshik6/HourVideo/hourvideo/form_world_state_history.py official repository unverified Apache-2.0 (permissive) · d21c0d0cbe00da28 · report
load_json keshik6/HourVideo/hourvideo/hv_utils.py official repository unverified Apache-2.0 (permissive) · 8ddb08051f41a1c4 · report
load_openai_client keshik6/HourVideo/hourvideo/gpt4_utils.py official repository unverified Apache-2.0 (permissive) · 8b1c14fc5481eb57 · report
load_yaml_files keshik6/HourVideo/hourvideo/hv_utils.py official repository unverified Apache-2.0 (permissive) · 6483832049cc55d0 · report
num_tokens_from_string keshik6/HourVideo/hourvideo/llm_utils.py official repository unverified Apache-2.0 (permissive) · dfc109b0a442de2e · report
preprocess_llm_output keshik6/HourVideo/hourvideo/llm_utils.py official repository unverified Apache-2.0 (permissive) · 5bf0c932374156bb · report
timestamp_to_seconds keshik6/HourVideo/hourvideo/gemini_utils.py official repository unverified Apache-2.0 (permissive) · 6ad55351c4f42d8f · report

Tasks

BenchmarkingMultiple-choiceRetrievalVisual Reasoning

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

HourVideo

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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