UAE Researchers Create First AI That Pinpoints Objects in Videos, Down to the Pixel

Authors: (1) Shehan Munasinghe, Mohamed bin Zayed University of AI and Equal Contribution; (2) Rusiru Thushara, Mohamed bin Zayed University of AI and Equal Contribution; (3) Muhammad Maaz, Mohamed bin Zayed University of AI; (4) Hanoona Abdul Rasheed, Mohamed bin Zayed University of AI; (5) Salman Khan, Mohamed bin Zayed University of AI and Australian National University; (6) Mubarak Shah, University of Central Florida; (7) Fahad Khan, Mohamed bin Zayed University of AI and Linköping University. Editor's Note: This is Part 9 of 10 of a study detailing the development of a smarter AI model for videos. Read the rest below. Table of Links Abstract and 1 Introduction 2. Related Works PG-Video-LLaVA 3.1. Overview 3.2. Architecture Experiments 4.1. Implementation Details 4.2. Stronger Baseline 4.3. Spatial Grounding in Videos 4.4. Zero-Shot Visual Question Answering 5. Conclusion and References Supplementary Material A. Audio Modality Integration B. Visual Grounding: Quantitative Evaluation C. Qualitative Results for Visual Grounding D. Quantitative Evaluations of Video-based Conversation Performance 5. Conclusion In this work, we introduced PG-Video-LLaVA, a novel video-based conversational model equipped with pixellevel grounding capabilities. PG-Video-LLaVA enhances image-based conversational models by extracting spatiotemporal features essential for comprehensive video understanding. It incorporates filtered audio transcripts to enrich the interpretation of visual scenes where audio cues are pivotal. Additionally, we developed a novel grounding module capable of tracking and generating pixel-level grounding of objects within videos. To promote reproducibility, we propose quantitative benchmarks for videobased conversational models, utilizing the open-sourced Vicuna LLM instead of GPT-3.5, as employed by previous approaches. These benchmarks are specifically designed to evaluate grounding capabilities. In summary, this work represents the first effort to integrate grounding capabilities into video-based LMMs. References [1] Pyscenedetect. https : / / github . com / Breakthrough / PySceneDetect, 2023. 5 [2] Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. Whisperx: Time-accurate speech transcription of longform audio. arXiv preprint arXiv:2303.00747, 2023. 3, 4, 1 [3] Hanoona Bangalath, Muhammad Maaz, Muhammad Uzair Khattak, Salman H Khan, and Fahad Shahbaz Khan. Bridging the gap between object and image-level representations for open-vocabulary detection. In NeurIPS, 2022. 2 [4] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, , Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020. 2 [5] Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. Shikra: Unleashing multimodal llm’s referential dialogue magic. arXiv preprint arXiv:2306.15195, 2023. 2 [6] Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander Schwing, and Joon-Young Lee. Tracking anything with decoupled video segmentation. In ICCV, 2023. 5 [7] Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https://vicuna. lmsys. org (accessed 14 April 2023), 2023. 2, 6 [8] Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. Instructblip: Towards generalpurpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500, 2023. 2 [9] Peng Gao, Jiaming Han, Renrui Zhang, Ziyi Lin, Shijie Geng, Aojun Zhou, Wei Zhang, Pan Lu, Conghui He, Xiangyu Yue, Hongsheng Li, and Yu Qiao. Llamaadapter v2: Parameter-efficient visual instruction model. arXiv:2304.15010, 2023. 2, 6, 8 [10] Yuan Gong, Sameer Khurana, Leonid Karlinsky, and James Glass. Whisper-at: Noise-robust automatic speech recognizers are also strong audio event taggers. In Proc. Interspeech 2023, 2023. 3, 4, 1 [11] Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, and Juan Carlos Niebles. Activitynet: A large-scale video benchmark for human activity understanding. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 961–970, 2015. 3, 7 [12] Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, and Ross Girshick. Segment anything. arXiv:2304.02643, 2023. 5 [13] Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, and Jiaya Jia. Lisa: Reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692, 2023. 2 [14] Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, and Ziwei Liu. Otter: A multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726, 2023. 2 [15] Kunchang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. Videochat: Chat-centric video understanding. arXiv:2305.06355, 2023. 1, 2, 6, 9 [16] Yuncheng Li, Yale Song, Liangliang Cao, Joel Tetreault, Larry Goldberg, Alejandro Jaimes, and Jiebo Luo. TGIF: A New Dataset and Benchmark on Animated GIF Description. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 7, 8 [17] Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, and Diana Marculescu. Open-vocabulary semantic segmentation with mask-adapted clip. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7061–7070, 2023. 2 [18] Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. ArXiv, abs/2304.08485, 2023. 2, 3 [19] Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. arXiv preprint arXiv:2304.08485, 2023. 2 [20] Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv:2303.05499, 2023. 5, 7 [21] Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, Shoufa Chen, Qinglong Zhang, Yang Yang, Qingyun Li, Jiashuo Yu, et al. Internchat: Solving vision-centric tasks by interacting with chatbots beyond language. arXiv preprint arXiv:2305.05662, 2023. 2 [22] Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv:2306.05424, 2023. 1, 2, 3, 5, 6, 7, 8 [23] Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, and Haibin Ling. Expanding language-image pretrained models for general video recognition. In European Conference on Computer Vision, pages 1–18. Springer, 2022. 2 [24] OpenAI. Whisper. https://openai.com/research/ whisper, 2022. 4, 1 [25] OpenAI. Gpt-4v(ision) system card. https://openai.com/ research/gpt-4v-system-card, 2023. 1 [26] OpenAI. Chatgpt: Large language model for human-style conversation. https://chat.openai.com, 2023. 2 [27] OpenLMLab. MOSS: Codebase for MOSS Project. https: //github.com/OpenLMLab/MOSS, 2023. 2 [28] Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35: 27730–27744, 2022. 2 [29] Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824, 2023. 2 [30] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In ICML, 2021. 2, 5 [31] Hanoona Rasheed, Muhammad Uzair Khattak, Muhammad Maaz, Salman Khan, and Fahad Shahbaz Khan. Fine-tuned clip models are efficient video learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6545–6554, 2023. 2 [32] Hanoona Rasheed, Muhammad Maaz, Sahal Shaji, Abdelrahman Shaker, Salman Khan, Hisham Cholakkal, Rao M Anwer, Erix Xing, Ming-Hsuan Yang, and Fahad S Khan. Glamm: Pixel grounding large multimodal model. arXiv preprint arXiv:2311.03356, 2023. 2 [33] David Rozenberszki, Or Litany, and Angela Dai. Languagegrounded indoor 3d semantic segmentation in the wild. In European Conference on Computer Vision, pages 125–141. Springer, 2022. 2 [34] Zongheng Tang, Yue Liao, Si Liu, Guanbin Li, Xiaojie Jin, Hongxu Jiang, Qian Yu, and Dong Xu. Human-centric spatio-temporal video grounding with visual transformers. IEEE Transactions on Circuits and Systems for Video Technology, 2021. 1, 5, 7 [35] Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B Hashimoto. Stanford alpaca: An instruction-following llama model, 2023. 2 [36] Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023. 2 [37] Mengmeng Wang, Jiazheng Xing, and Yong Liu. Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472, 2021. 2 [38] Weiyun Wang, Min Shi, Qingyun Li, Wenhai Wang, Zhenhang Huang, Linjie Xing, Zhe Chen, Hao Li, Xizhou Zhu, Zhiguo Cao, et al. The all-seeing project: Towards panoptic visual recognition and understanding of the open world. arXiv preprint arXiv:2308.01907, 2023. 2 [39] Dejing Xu, Zhou Zhao, Jun Xiao, Fei Wu, Hanwang Zhang, Xiangnan He, and Yueting Zhuang. Video question answering via gradually refined attention over appearance and motion. In ACM Multimedia, 2017. 7, 8 [40] Jun Xu, Tao Mei, Ting Yao, and Yong Rui. Msr-vtt: A large video description dataset for bridging video and language. 2016. 7, 8 [41] Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, and Cordelia Schmid. Zero-shot video question answering via frozen bidirectional language models. In NeurIPS, 2022. 8, 9 [42] Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye, Ming Yan, Yiyang Zhou, Junyang Wang, Anwen Hu, Pengcheng Shi, Yaya Shi, et al. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178, 2023. 2 [43] Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, and Yinfei Yang. Ferret: Refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704, 2023. 2 [44] Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, and Dacheng Tao. Activitynet-qa: A dataset for understanding complex web videos via question answering. In AAAI, pages 9127–9134, 2019. 7, 8 [45] Hang Zhang, Xin Li, and Lidong Bing. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv:2306.02858, 2023. 1, 2, 6, 7, 8 [46] Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068, 2022. 2 [47] Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, et al. Recognize anything: A strong image tagging model. arXiv preprint arXiv:2306.03514, 2023. 5 [48] Zhu Zhang, Zhou Zhao, Yang Zhao, Qi Wang, Huasheng Liu, and Lianli Gao. Where does it exist: Spatio-temporal video grounding for multi-form sentences. In CVPR, 2020. 1, 5, 7, 6 [49] Yang Zhao, Zhijie Lin, Daquan Zhou, Zilong Huang, Jiashi Feng, and Bingyi Kang. Bubogpt: Enabling visual grounding in multi-modal llms. arXiv preprint arXiv:2307.08581, 2023. 2, 5, 3 [50] Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592, 2023. 2 This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Shehan Munasinghe, Mohamed bin Zayed University of AI and Equal Contribution; (2) Rusiru Thushara, Mohamed bin Zayed University of AI and Equal Contribution; (3) Muhammad Maaz, Mohamed bin Zayed University of AI; (4) Hanoona Abdul Rasheed, Mohamed bin Zayed University of AI; (5) Salman Khan, Mohamed bin Zayed University of AI and Australian National University; (6) Mubarak Shah, University of Central Florida; (7) Fahad Khan, Mohamed bin Zayed University of AI and Linköping University. Authors: Authors: (1) Shehan Munasinghe, Mohamed bin Zayed University of AI and Equal Contribution; (2) Rusiru Thushara, Mohamed bin Zayed University of AI and Equal Contribution; (3) Muhammad Maaz, Mohamed bin Zayed University of AI; (4) Hanoona Abdul Rasheed, Mohamed bin Zayed University of AI; (5) Salman Khan, Mohamed bin Zayed University of AI and Australian National University; (6) Mubarak Shah, University of Central Florida; (7) Fahad Khan, Mohamed bin Zayed University of AI and Linköping University. Editor's Note: This is Part 9 of 10 of a study detailing the development of a smarter AI model for videos. Read the rest below. Editor's Note: This is Part 9 of 10 of a study detailing the development of a smarter AI model for videos. Read the rest below. Editor's Note: This is Part 9 of 10 of a study detailing the development of a smarter AI model for videos. Read the rest below. Editor's Note: This is Part 9 of 10 of a study detailing the development of a smarter AI model for videos. Read the rest below. Table of Links Abstract and 1 Introduction 2. Related Works PG-Video-LLaVA 3.1. Overview 3.2. Architecture Experiments 4.1. Implementation Details 4.2. Stronger Baseline 4.3. Spatial Grounding in Videos 4.4. Zero-Shot Visual Question Answering 5. Conclusion and References Abstract and 1 Introduction Abstract and 1 Introduction 2. Related Works 2. Related Works PG-Video-LLaVA PG-Video-LLaVA PG-Video-LLaVA 3.1. Overview 3.1. Overview 3.2. Architecture 3.2. Architecture Experiments Experiments Experiments 4.1. Implementation Details 4.1. Implementation Details 4.2. Stronger Baseline 4.2. Stronger Baseline 4.3. Spatial Grounding in Videos 4.3. Spatial Grounding in Videos 4.4. Zero-Shot Visual Question Answering 4.4. Zero-Shot Visual Question Answering 5. Conclusion and References 5. Conclusion and References Supplementary Material Supplementary Material A. Audio Modality Integration B. Visual Grounding: Quantitative Evaluation C. Qualitative Results for Visual Grounding D. Quantitative Evaluations of Video-based Conversation Performance A. Audio Modality Integration A. Audio Modality Integration B. Visual Grounding: Quantitative Evaluation B. Visual Grounding: Quantitative Evaluation C. Qualitative Results for Visual Grounding C. Qualitative Results for Visual Grounding D. Quantitative Evaluations of Video-based Conversation Performance D. Quantitative Evaluations of Video-based Conversation Performance 5. Conclusion In this work, we introduced PG-Video-LLaVA, a novel video-based conversational model equipped with pixellevel grounding capabilities. PG-Video-LLaVA enhances image-based conversational models by extracting spatiotemporal features essential for comprehensive video understanding. It incorporates filtered audio transcripts to enrich the interpretation of visual scenes where audio cues are pivotal. Additionally, we developed a novel grounding module capable of tracking and generating pixel-level grounding of objects within videos. To promote reproducibility, we propose quantitative benchmarks for videobased conversational models, utilizing the open-sourced Vicuna LLM instead of GPT-3.5, as employed by previous approaches. These benchmarks are specifically designed to evaluate grounding capabilities. In summary, this work represents the first effort to integrate grounding capabilities into video-based LMMs. References [1] Pyscenedetect. https : / / github . com / Breakthrough / PySceneDetect, 2023. 5 [2] Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. Whisperx: Time-accurate speech transcription of longform audio. arXiv preprint arXiv:2303.00747, 2023. 3, 4, 1 [3] Hanoona Bangalath, Muhammad Maaz, Muhammad Uzair Khattak, Salman H Khan, and Fahad Shahbaz Khan. Bridging the gap between object and image-level representations for open-vocabulary detection. In NeurIPS, 2022. 2 [4] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, , Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020. 2 [5] Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. Shikra: Unleashing multimodal llm’s referential dialogue magic. arXiv preprint arXiv:2306.15195, 2023. 2 [6] Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander Schwing, and Joon-Young Lee. Tracking anything with decoupled video segmentation. In ICCV, 2023. 5 [7] Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https://vicuna . lmsys. org (accessed 14 April 2023), 2023. 2, 6 https://vicuna [8] Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. Instructblip: Towards generalpurpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500, 2023. 2 [9] Peng Gao, Jiaming Han, Renrui Zhang, Ziyi Lin, Shijie Geng, Aojun Zhou, Wei Zhang, Pan Lu, Conghui He, Xiangyu Yue, Hongsheng Li, and Yu Qiao. Llamaadapter v2: Parameter-efficient visual instruction model. arXiv:2304.15010, 2023. 2, 6, 8 [10] Yuan Gong, Sameer Khurana, Leonid Karlinsky, and James Glass. Whisper-at: Noise-robust automatic speech recognizers are also strong audio event taggers. In Proc. Interspeech 2023, 2023. 3, 4, 1 [11] Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, and Juan Carlos Niebles. Activitynet: A large-scale video benchmark for human activity understanding. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 961–970, 2015. 3, 7 [12] Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, and Ross Girshick. Segment anything. arXiv:2304.02643, 2023. 5 [13] Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, and Jiaya Jia. Lisa: Reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692, 2023. 2 [14] Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, and Ziwei Liu. Otter: A multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726, 2023. 2 [15] Kunchang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. Videochat: Chat-centric video understanding. arXiv:2305.06355, 2023. 1, 2, 6, 9 [16] Yuncheng Li, Yale Song, Liangliang Cao, Joel Tetreault, Larry Goldberg, Alejandro Jaimes, and Jiebo Luo. TGIF: A New Dataset and Benchmark on Animated GIF Description. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 7, 8 [17] Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, and Diana Marculescu. Open-vocabulary semantic segmentation with mask-adapted clip. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7061–7070, 2023. 2 [18] Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. ArXiv, abs/2304.08485, 2023. 2, 3 [19] Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. arXiv preprint arXiv:2304.08485, 2023. 2 [20] Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv:2303.05499, 2023. 5, 7 [21] Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, Shoufa Chen, Qinglong Zhang, Yang Yang, Qingyun Li, Jiashuo Yu, et al. Internchat: Solving vision-centric tasks by interacting with chatbots beyond language. arXiv preprint arXiv:2305.05662, 2023. 2 [22] Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv:2306.05424, 2023. 1, 2, 3, 5, 6, 7, 8 [23] Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, and Haibin Ling. Expanding language-image pretrained models for general video recognition. In European Conference on Computer Vision, pages 1–18. Springer, 2022. 2 [24] OpenAI. Whisper. https://openai.com/research/ whisper, 2022. 4, 1 [25] OpenAI. Gpt-4v(ision) system card. https://openai.com/ research/gpt-4v-system-card, 2023. 1 [26] OpenAI. Chatgpt: Large language model for human-style conversation. https://chat.openai.com, 2023. 2 [27] OpenLMLab. MOSS: Codebase for MOSS Project. https: //github.com/OpenLMLab/MOSS, 2023. 2 [28] Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35: 27730–27744, 2022. 2 [29] Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824, 2023. 2 [30] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In ICML, 2021. 2, 5 [31] Hanoona Rasheed, Muhammad Uzair Khattak, Muhammad Maaz, Salman Khan, and Fahad Shahbaz Khan. Fine-tuned clip models are efficient video learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6545–6554, 2023. 2 [32] Hanoona Rasheed, Muhammad Maaz, Sahal Shaji, Abdelrahman Shaker, Salman Khan, Hisham Cholakkal, Rao M Anwer, Erix Xing, Ming-Hsuan Yang, and Fahad S Khan. Glamm: Pixel grounding large multimodal model. arXiv preprint arXiv:2311.03356, 2023. 2 [33] David Rozenberszki, Or Litany, and Angela Dai. Languagegrounded indoor 3d semantic segmentation in the wild. In European Conference on Computer Vision, pages 125–141. Springer, 2022. 2 [34] Zongheng Tang, Yue Liao, Si Liu, Guanbin Li, Xiaojie Jin, Hongxu Jiang, Qian Yu, and Dong Xu. Human-centric spatio-temporal video grounding with visual transformers. IEEE Transactions on Circuits and Systems for Video Technology, 2021. 1, 5, 7 [35] Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B Hashimoto. Stanford alpaca: An instruction-following llama model, 2023. 2 [36] Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023. 2 [37] Mengmeng Wang, Jiazheng Xing, and Yong Liu. Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472, 2021. 2 [38] Weiyun Wang, Min Shi, Qingyun Li, Wenhai Wang, Zhenhang Huang, Linjie Xing, Zhe Chen, Hao Li, Xizhou Zhu, Zhiguo Cao, et al. The all-seeing project: Towards panoptic visual recognition and understanding of the open world. arXiv preprint arXiv:2308.01907, 2023. 2 [39] Dejing Xu, Zhou Zhao, Jun Xiao, Fei Wu, Hanwang Zhang, Xiangnan He, and Yueting Zhuang. Video question answering via gradually refined attention over appearance and motion. In ACM Multimedia, 2017. 7, 8 [40] Jun Xu, Tao Mei, Ting Yao, and Yong Rui. Msr-vtt: A large video description dataset for bridging video and language. 2016. 7, 8 [41] Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, and Cordelia Schmid. Zero-shot video question answering via frozen bidirectional language models. In NeurIPS, 2022. 8, 9 [42] Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye, Ming Yan, Yiyang Zhou, Junyang Wang, Anwen Hu, Pengcheng Shi, Yaya Shi, et al. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178, 2023. 2 [43] Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, and Yinfei Yang. Ferret: Refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704, 2023. 2 [44] Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, and Dacheng Tao. Activitynet-qa: A dataset for understanding complex web videos via question answering. In AAAI, pages 9127–9134, 2019. 7, 8 [45] Hang Zhang, Xin Li, and Lidong Bing. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv:2306.02858, 2023. 1, 2, 6, 7, 8 [46] Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068, 2022. 2 [47] Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, et al. Recognize anything: A strong image tagging model. arXiv preprint arXiv:2306.03514, 2023. 5 [48] Zhu Zhang, Zhou Zhao, Yang Zhao, Qi Wang, Huasheng Liu, and Lianli Gao. Where does it exist: Spatio-temporal video grounding for multi-form sentences. In CVPR, 2020. 1, 5, 7, 6 [49] Yang Zhao, Zhijie Lin, Daquan Zhou, Zilong Huang, Jiashi Feng, and Bingyi Kang. Bubogpt: Enabling visual grounding in multi-modal llms. arXiv preprint arXiv:2307.08581, 2023. 2, 5, 3 [50] Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592, 2023. 2 This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv