{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","arxiv_id":"2403.18406","date":"2024-03-27","proceeding":null,"authors":["Wonkyun Kim","Changin Choi","Wonseok Lee","Wonjong Rhee"],"abstract":"Stimulated by the sophisticated reasoning capabilities of recent Large Language Models (LLMs), a variety of strategies for bridging video modality have been devised. A prominent strategy involves Video Language Models (VideoLMs), which train a learnable interface with video data to connect advanced vision encoders with LLMs. Recently, an alternative strategy has surfaced, employing readily available foundation models, such as VideoLMs and LLMs, across multiple stages for modality bridging. In this study, we introduce a simple yet novel strategy where only a single Vision Language Model (VLM) is utilized. Our starting point is the plain insight that a video comprises a series of images, or frames, interwoven with temporal information. The essence of video comprehension lies in adeptly managing the temporal aspects along with the spatial details of each frame. Initially, we transform a video into a single composite image by arranging multiple frames in a grid layout. The resulting single image is termed as an image grid. This format, while maintaining the appearance of a solitary image, effectively retains temporal information within the grid structure. Therefore, the image grid approach enables direct application of a single high-performance VLM without necessitating any video-data training. Our extensive experimental analysis across ten zero-shot video question answering benchmarks, including five open-ended and five multiple-choice benchmarks, reveals that the proposed Image Grid Vision Language Model (IG-VLM) surpasses the existing methods in nine out of ten benchmarks.","url_abs":"https://arxiv.org/abs/2403.18406v1","url_pdf":"https://arxiv.org/pdf/2403.18406v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-image-grid-can-be-worth-a-video-zero-shot","repo_url":"https://github.com/imagegridworth/IG-VLM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-based-generative-performance","task_name":"Video-based Generative Performance Benchmarking"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-based-generative-performance","task":"Video-based Generative Performance Benchmarking","dataset":"VideoInstruct","model":"IG-VLM-GPT4v","rank_in_archive_order":8,"of":23,"metrics":{"Consistency":"3.13","Contextual Understanding":"3.61","Correctness of Information":"3.40","Detail Orientation":"2.80","Temporal Understanding":"2.89","mean":"3.17"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"IG-VLM","rank_in_archive_order":7,"of":28,"metrics":{"Accuracy":"58.4","Confidence Score":"3.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-intentqa","task":"Zero-Shot Video Question Answer","dataset":"IntentQA","model":"IG-VLM","rank_in_archive_order":6,"of":13,"metrics":{"Accuracy":"65.3"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","task":"Zero-Shot Video Question Answer","dataset":"MSRVTT-QA","model":"IG-VLM","rank_in_archive_order":9,"of":30,"metrics":{"Accuracy":"63.8","Confidence Score":"3.5"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","task":"Zero-Shot Video Question Answer","dataset":"MSVD-QA","model":"IG-VLM-34B","rank_in_archive_order":7,"of":28,"metrics":{"Accuracy":"79.6","Confidence Score":"4.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"IG-VLM(LLaVA v1.6)","rank_in_archive_order":9,"of":27,"metrics":{"Accuracy":"70.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"IG-VLM (GPT-4)","rank_in_archive_order":12,"of":27,"metrics":{"Accuracy":"68.6"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-tgif-qa","task":"Zero-Shot Video Question Answer","dataset":"TGIF-QA","model":"IG-VLM","rank_in_archive_order":6,"of":14,"metrics":{"Accuracy":"79.1","Confidence Score":"4.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-tvqa","task":"Zero-Shot Video Question Answer","dataset":"TVQA","model":"IG-VLM (no speech, GPT-4V)","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"57.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imagegridworth/IG-VLM","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"27990140245e0f68","entry":"get_llava_and_prompt","repo":"imagegridworth/IG-VLM","repo_kind":"official","path":"eval_llava_openended.py","file_url":"https://github.com/imagegridworth/IG-VLM/blob/HEAD/eval_llava_openended.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"27990140245e0f68"}},{"code_sha256_prefix":"c3ad8f46bb951fab","entry":"validate_llm_size","repo":"imagegridworth/IG-VLM","repo_kind":"official","path":"eval_llava_openended.py","file_url":"https://github.com/imagegridworth/IG-VLM/blob/HEAD/eval_llava_openended.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c3ad8f46bb951fab"}},{"code_sha256_prefix":"5f5e72c2cae176b2","entry":"validate_video_path","repo":"imagegridworth/IG-VLM","repo_kind":"official","path":"eval_llava_openended.py","file_url":"https://github.com/imagegridworth/IG-VLM/blob/HEAD/eval_llava_openended.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5f5e72c2cae176b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}