{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=2311.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13435"}},"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/mbzuai-oryx/video-llava","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":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,"samples":[{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37fcf26fc4a105af"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5764189adab1c8ff"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37899f22fb191b37"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"54b2d55aa476a3bc"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}