Browse State-of-the-Art › Zero-Shot Video Question Answer

Zero-Shot Video Question Answer

73 papers with code · 17 benchmarks · 18 datasets archive 2025-07-28

Computer VisionMiscellaneousNatural Language ProcessingReasoning

This task present the results of Zeroshot Question Answer results on TGIF-QA dataset for LLM powered Video Conversational Models.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

17 leaderboard tables shown for this task, 17 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 17 until expanded.

Syntology 10 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): MSRVTT-QA (2 judged, 0 placed), ActivityNet-QA (1 judged, 0 placed), MSVD-QA (1 judged, 0 placed), NExT-QA (2 judged, 0 placed), EgoSchema (subset) (1 judged, 0 placed), TGIF-QA (1 judged, 0 placed), IntentQA (2 judged, 0 placed), Video-MME (3 judged, 0 placed), VNBench (1 judged, 0 placed), MVBench (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MSRVTT-QA (30 rows) Flash-VStream Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams code — Compare
EgoSchema (fullset) (29 rows) BIMBA-LLaVA-Qwen2-7B BIMBA: Selective-Scan Compression for Long-Range Video Question Answering code — Compare
ActivityNet-QA (28 rows) Tarsier (34B) Tarsier: Recipes for Training and Evaluating Large Video Description Models code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
MSVD-QA (28 rows) Tarsier (34B) Tarsier: Recipes for Training and Evaluating Large Video Description Models code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
NExT-QA (27 rows) VideoMultiAgent (GPT-4o) VideoMultiAgents: A Multi-Agent Framework for Video Question Answering code — Compare
EgoSchema (subset) (14 rows) Tarsier (34B) Tarsier: Recipes for Training and Evaluating Large Video Description Models code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
TGIF-QA (14 rows) Tarsier (34B) Tarsier: Recipes for Training and Evaluating Large Video Description Models code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
IntentQA (13 rows) ENTER ENTER: Event Based Interpretable Reasoning for VideoQA — — Compare
Video-MME (11 rows) Gemini 1.5 Pro Gemini 1.5: Unlocking multimodal understanding across millions of... code — Compare
NExT-GQA (9 rows) DeVi (Gemini 2.0) Question-Answering Dense Video Events code — Compare
TVQA (9 rows) FrozenBiLM (with speech) Zero-Shot Video Question Answering via Frozen Bidirectional Language Models code Syntology official: harvested, nothing ran · 14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified Compare
Video-MME (w/o subs) (9 rows) Video-RAG (based on LLaVA-Video) Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension code Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
VNBench (9 rows) BIMBA-LLaVA-Qwen2-7B BIMBA: Selective-Scan Compression for Long-Range Video Question Answering code — Compare
STAR Benchmark (4 rows) VideoChat2 MVBench: A Comprehensive Multi-modal Video Understanding Benchmark code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified Compare
Zero-shot Video Question Answering on LongVideoBench (4 rows) Gemini 1.5 Pro Gemini 1.5: Unlocking multimodal understanding across millions of... code — Compare
MVBench (2 rows) TS-LLaVA-34B TS-LLaVA: Constructing Visual Tokens through... code Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified Compare
CinePile: A Long Video Question Answering Dataset and Benchmark (1 row) Human CinePile: A Long Video Question Answering Dataset and Benchmark — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

18 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 85 · with a code link: 73 · where Syntology ran a sample: 45 (38 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (45 of 85 tagged: 38 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 85 of 85, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 47 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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