{"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/vtg-gpt-tuning-free-zero-shot-video-temporal-1","title":"VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT","arxiv_id":"2403.02076","date":"2024-03-04","proceeding":"Applied Sciences 2024 2","authors":["Yifang Xu","Yunzhuo Sun","Zien Xie","Benxiang Zhai","Sidan Du"],"abstract":"Video temporal grounding (VTG) aims to locate specific temporal segments from an untrimmed video based on a linguistic query. Most existing VTG models are trained on extensive annotated video-text pairs, a process that not only introduces human biases from the queries but also incurs significant computational costs. To tackle these challenges, we propose VTG-GPT, a GPT-based method for zero-shot VTG without training or fine-tuning. To reduce prejudice in the original query, we employ Baichuan2 to generate debiased queries. To lessen redundant information in videos, we apply MiniGPT-v2 to transform visual content into more precise captions. Finally, we devise the proposal generator and post-processing to produce accurate segments from debiased queries and image captions. Extensive experiments demonstrate that VTG-GPT significantly outperforms SOTA methods in zero-shot settings and surpasses unsupervised approaches. More notably, it achieves competitive performance comparable to supervised methods. The code is available on https://github.com/YoucanBaby/VTG-GPT","url_abs":"https://arxiv.org/abs/2403.02076v1","url_pdf":"https://arxiv.org/pdf/2403.02076v1.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":"vtg-gpt-tuning-free-zero-shot-video-temporal-1","repo_url":"https://github.com/YoucanBaby/VTG-GPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"zero-shot-moment-retrieval","task_name":"Zero-shot Moment Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-moment-retrieval-on-qvhighlights","task":"Zero-shot Moment Retrieval","dataset":"QVHighlights","model":"VTG-GPT","rank_in_archive_order":2,"of":2,"metrics":{"R1@0.5":"54.26","R1@0.7":"38.45","mAP":"30.91","mAP@0.5":"54.17","mAP@0.75":"29.73"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.02076","atlas_url":"https://app.syntology.ai/?focus=2403.02076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02076"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/YoucanBaby/VTG-GPT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran":4,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":"f8e4c1c5aac977d6","entry":"computeIoU","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"minigpt/demo_v2.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/minigpt/demo_v2.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8e4c1c5aac977d6"}},{"code_sha256_prefix":"66a6e11c5d2b4b00","entry":"compute_temporal_iou_batch_cross","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"standalone_eval/utils.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/standalone_eval/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66a6e11c5d2b4b00"}},{"code_sha256_prefix":"7069f9c03e6dffb9","entry":"compute_temporal_iou_batch_paired","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"standalone_eval/utils.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/standalone_eval/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7069f9c03e6dffb9"}},{"code_sha256_prefix":"5c3e6655c3b3e958","entry":"extract_substrings","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"minigpt/demo_v2.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/minigpt/demo_v2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c3e6655c3b3e958"}},{"code_sha256_prefix":"37438be3369e6493","entry":"is_overlapping","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"minigpt/demo_v2.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/minigpt/demo_v2.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37438be3369e6493"}},{"code_sha256_prefix":"2d946250dd2f5a4f","entry":"load_json","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"standalone_eval/file_utils.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/standalone_eval/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d946250dd2f5a4f"}},{"code_sha256_prefix":"f1d1cccccf038785","entry":"load_jsonl","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"standalone_eval/file_utils.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/standalone_eval/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1d1cccccf038785"}},{"code_sha256_prefix":"570ad34bd1af44a8","entry":"load_pickle","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"standalone_eval/file_utils.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/standalone_eval/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"570ad34bd1af44a8"}},{"code_sha256_prefix":"1cad4da14d13ad59","entry":"print_running_time","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"Baichuan2/rephrase_query.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/Baichuan2/rephrase_query.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1cad4da14d13ad59"}},{"code_sha256_prefix":"2de73df87fce327d","entry":"chat","repo":"YoucanBaby/VTG-GPT","repo_kind":"official","path":"Baichuan2/rephrase_query.py","file_url":"https://github.com/YoucanBaby/VTG-GPT/blob/HEAD/Baichuan2/rephrase_query.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2de73df87fce327d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}