{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/pg-video-llava-pixel-grounding-large-video","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","arxiv_id":"2311.13435","date":"2023-11-22","proceeding":null,"authors":["Shehan Munasinghe","Rusiru Thushara","Muhammad Maaz","Hanoona Abdul Rasheed","Salman Khan","Mubarak Shah","Fahad Khan"],"abstract":"Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose PG-Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker and a novel grounding module, enabling it to spatially localize objects in videos following user instructions. We evaluate PG-Video-LLaVA using video-based generative and question-answering benchmarks and introduce new benchmarks specifically designed to measure prompt-based object grounding performance in videos. Further, we propose the use of Vicuna over GPT-3.5, as utilized in Video-ChatGPT, for video-based conversation benchmarking, ensuring reproducibility of results which is a concern with the proprietary nature of GPT-3.5. Our framework builds on SoTA image-based LLaVA model and extends its advantages to the video domain, delivering promising gains on video-based conversation and grounding tasks. Project Page: https://github.com/mbzuai-oryx/Video-LLaVA","url_abs":"https://arxiv.org/abs/2311.13435v2","url_pdf":"https://arxiv.org/pdf/2311.13435v2.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":"pg-video-llava-pixel-grounding-large-video","repo_url":"https://github.com/mbzuai-oryx/video-llava","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"spatio-temporal-video-grounding","task_name":"Spatio-Temporal Video Grounding"},{"task_slug":"video-grounding","task_name":"Video Grounding"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.13435","atlas_url":"https://app.syntology.ai/?focus=2311.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13435"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.13435"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.13435"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.13435\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2311.13435"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.13435\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.13435"},"call":"get_concepts_for_paper(arxiv_id=\"2311.13435\")"}],"by_repo":[{"repo":"mbzuai-oryx/video-llava","kind":"official","samples":5,"ran":3,"instrument":1,"unverified":2}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2311.13435.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2311.13435.svg"},"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/mbzuai-oryx/video-llava","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_violates":1,"unverified":2},"n_samples":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":5,"ran":3,"n_ran_checked":2,"n_instrument":1,"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":5,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":3,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"5764189adab1c8ff","code_sha256_prefix":"5764189adab1c8ff","entry":"get_seq_frames","repo":"mbzuai-oryx/video-llava","repo_kind":"official","path":"video_chatgpt/eval/model_utils.py","file_url":"https://github.com/mbzuai-oryx/video-llava/blob/HEAD/video_chatgpt/eval/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"total_num_frames:int/0/int, desired_num_frames:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5764189adab1c8ff"},"code_page":"/code/get-seq-frames","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mbzuai-oryx/video-llava when it was checked","mcp_get_code":{"code_sha256":"5764189adab1c8ff"}},{"code_sha256":"37fcf26fc4a105af","code_sha256_prefix":"37fcf26fc4a105af","entry":"get_spatio_temporal_features_torch","repo":"mbzuai-oryx/video-llava","repo_kind":"official","path":"video_chatgpt/inference.py","file_url":"https://github.com/mbzuai-oryx/video-llava/blob/HEAD/video_chatgpt/inference.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"features:Tensor/3/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"37fcf26fc4a105af"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mbzuai-oryx/video-llava when it was checked","mcp_get_code":{"code_sha256":"37fcf26fc4a105af"}},{"code_sha256":"f9939a84b9a65279","code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"mbzuai-oryx/video-llava","repo_kind":"official","path":"video_chatgpt/utils.py","file_url":"https://github.com/mbzuai-oryx/video-llava/blob/HEAD/video_chatgpt/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"text:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/violates-moderation","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mbzuai-oryx/video-llava when it was checked","mcp_get_code":{"code_sha256":"f9939a84b9a65279"}},{"code_sha256":"37899f22fb191b37","code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"mbzuai-oryx/video-llava","repo_kind":"official","path":"video_chatgpt/utils.py","file_url":"https://github.com/mbzuai-oryx/video-llava/blob/HEAD/video_chatgpt/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/pretty-print-semaphore","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mbzuai-oryx/video-llava when it was checked","mcp_get_code":{"code_sha256":"37899f22fb191b37"}},{"code_sha256":"54b2d55aa476a3bc","code_sha256_prefix":"54b2d55aa476a3bc","entry":"unwrap_model","repo":"mbzuai-oryx/video-llava","repo_kind":"official","path":"video_chatgpt/train/llava_trainer.py","file_url":"https://github.com/mbzuai-oryx/video-llava/blob/HEAD/video_chatgpt/train/llava_trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/unwrap-model","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mbzuai-oryx/video-llava when it was checked","mcp_get_code":{"code_sha256":"54b2d55aa476a3bc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9f8882ba2ba4c2f9b5dfe6c22a06700ec4607edc0c968220af1665d50f4f3fcd","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}