Kanchana Ranasinghe

43 papers A* 9A 1Misc 1Journal 27Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Future Optical Flow Prediction Improves Robot Control & Video Generation. CoRR Kanchana Ranasinghe, Honglu Zhou, Yu Fang, Luyu Yang, Le Xue, Ran Xu, Caiming Xiong, Silvio Savarese, Michael S. Ryoo, Juan Carlos Niebles
2026	J	`jnl`	IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance. CoRR Jongwoo Park, Kanchana Ranasinghe, Jinhyeok Jang, Cristina Mata, Yoo Sung Jang, Michael S. Ryoo
2026	—	`conf`	Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA. EACL (Volume 1: Long Papers) Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya, Wonjeong Ryu, Donghyun Kim, Michael S. Ryoo
2025	J	`jnl`	CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings. CoRR Cristina Mata, Kanchana Ranasinghe, Michael S. Ryoo
2025	A*	`conf`	LLaRA: Supercharging Robot Learning Data for Vision-Language Policy. ICLR Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan D. Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo
2025	—	`conf`	Language Repository for Long Video Understanding. ACL (Findings) Kumara Kahatapitiya, Kanchana Ranasinghe, Jongwoo Park, Michael S. Ryoo
2025	J	`jnl`	Pixel Motion Diffusion is What We Need for Robot Control. CoRR E-Ro Nguyen, Yichi Zhang, Kanchana Ranasinghe, Xiang Li, Michael S. Ryoo
2025	J	`jnl`	Pixel Motion as Universal Representation for Robot Control. CoRR Kanchana Ranasinghe, Xiang Li, Cristina Mata, Jongwoo Park, Michael S. Ryoo
2025	J	`jnl`	Robotic VLA Benefits from Joint Learning with Motion Image Diffusion. CoRR Yu Fang, Kanchana Ranasinghe, Le Xue, Honglu Zhou, Juntao Tan, Ran Xu, Shelby Heinecke, Caiming Xiong, Silvio Savarese, Daniel Szafir, Mingyu Ding, Michael S. Ryoo, Juan Carlos Niebles
2025	J	`jnl`	Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation. CoRR Ulindu De Silva, Didula Samaraweera, Sasini Wanigathunga, Kavindu Kariyawasam, Kanchana Ranasinghe, Muzammal Naseer, Ranga Rodrigo
2025	A*	`conf`	Understanding Long Videos with Multimodal Language Models. ICLR Kanchana Ranasinghe, Xiang Li, Kumara Kahatapitiya, Michael S. Ryoo
2024	—	`conf`	CoPT: Unsupervised Domain Adaptive Segmentation Using Domain-Agnostic Text Embeddings. ECCV (62) Cristina Mata, Kanchana Ranasinghe, Michael S. Ryoo
2024	—	`conf`	Diffusion Illusions: Hiding Images in Plain Sight. SIGGRAPH (Conference Paper Track) Ryan D. Burgert, Xiang Li, Abe Leite, Kanchana Ranasinghe, Michael S. Ryoo
2024	—	`conf`	Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning. MICCAI (4) Hasindri Watawana, Kanchana Ranasinghe, Tariq Mahmood, Muzammal Naseer, Salman H. Khan, Fahad Shahbaz Khan
2024	J	`jnl`	Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning. CoRR Hasindri Watawana, Kanchana Ranasinghe, Tariq Mahmood, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan
2024	J	`jnl`	LLaRA: Supercharging Robot Learning Data for Vision-Language Policy. CoRR Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan D. Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo
2024	J	`jnl`	Language Repository for Long Video Understanding. CoRR Kumara Kahatapitiya, Kanchana Ranasinghe, Jongwoo Park, Michael S. Ryoo
2024	J	`jnl`	LatentCRF: Continuous CRF for Efficient Latent Diffusion. CoRR Kanchana Ranasinghe, Sadeep Jayasumana, Andreas Veit, Ayan Chakrabarti, Daniel Glasner, Michael S. Ryoo, Srikumar Ramalingam, Sanjiv Kumar
2024	A*	`conf`	Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs. CVPR Kanchana Ranasinghe, Satya Narayan Shukla, Omid Poursaeed, Michael S. Ryoo, Tsung-Yu Lin
2024	J	`jnl`	Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs. CoRR Kanchana Ranasinghe, Satya Narayan Shukla, Omid Poursaeed, Michael S. Ryoo, Tsung-Yu Lin
2024	J	`jnl`	Too Many Frames, not all Useful: Efficient Strategies for Long-Form Video QA. CoRR Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya, Wonjeong Ryoo, Donghyun Kim, Michael S. Ryoo
2024	J	`jnl`	Understanding Long Videos in One Multimodal Language Model Pass. CoRR Kanchana Ranasinghe, Xiang Li, Kumara Kahatapitiya, Michael S. Ryoo
2023	J	`jnl`	Diffusion Illusions: Hiding Images in Plain Sight. CoRR Ryan D. Burgert, Xiang Li, Abe Leite, Kanchana Ranasinghe, Michael S. Ryoo
2023	A*	`conf`	Language-based Action Concept Spaces Improve Video Self-Supervised Learning. NeurIPS Kanchana Ranasinghe, Michael S. Ryoo
2023	J	`jnl`	Language-based Action Concept Spaces Improve Video Self-Supervised Learning. CoRR Kanchana Ranasinghe, Michael S. Ryoo
2023	A*	`conf`	Perceptual Grouping in Contrastive Vision-Language Models. ICCV Kanchana Ranasinghe, Brandon McKinzie, Sachin Ravi, Yinfei Yang, Alexander Toshev, Jonathon Shlens
2022	A*	`conf`	On Improving Adversarial Transferability of Vision Transformers. ICLR Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Fahad Shahbaz Khan, Fatih Porikli
2022	J	`jnl`	Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors. CoRR Ryan D. Burgert, Kanchana Ranasinghe, Xiang Li, Michael S. Ryoo
2022	J	`jnl`	Perceptual Grouping in Vision-Language Models. CoRR Kanchana Ranasinghe, Brandon McKinzie, Sachin Ravi, Yinfei Yang, Alexander Toshev, Jonathon Shlens
2022	A*	`conf`	Self-supervised Video Transformer. CVPR Kanchana Ranasinghe, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan, Michael S. Ryoo
2021	A*	`conf`	Intriguing Properties of Vision Transformers. NeurIPS Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang
2021	J	`jnl`	Intriguing Properties of Vision Transformers. CoRR Muzammal Naseer, Kanchana Ranasinghe, Salman H. Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang
2021	J	`jnl`	On Improving Adversarial Transferability of Vision Transformers. CoRR Muzammal Naseer, Kanchana Ranasinghe, Salman H. Khan, Fahad Shahbaz Khan, Fatih Porikli
2021	A*	`conf`	Orthogonal Projection Loss. ICCV Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat, Salman H. Khan, Fahad Shahbaz Khan
2021	J	`jnl`	Orthogonal Projection Loss. CoRR Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat, Salman H. Khan, Fahad Shahbaz Khan
2021	J	`jnl`	Self-supervised Video Transformer. CoRR Kanchana Ranasinghe, Muzammal Naseer, Salman H. Khan, Fahad Shahbaz Khan, Michael S. Ryoo
2020	A	`conf`	Bipartite Conditional Random Fields for Panoptic Segmentation. BMVC Sadeep Jayasumana, Kanchana Ranasinghe, Sahan Liyanaarachchi, Mayuka Jayawardhana, Harsha Ranasinghe, Sina Samangooei
2020	J	`jnl`	Conditional Generative Modeling via Learning the Latent Space. CoRR Sameera Ramasinghe, Kanchana Ranasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2019	J	`jnl`	Bipartite Conditional Random Fields for Panoptic Segmentation. CoRR Sadeep Jayasumana, Kanchana Ranasinghe, Mayuka Jayawardhana, Sahan Liyanaarachchi, Harsha Ranasinghe
2019	J	`jnl`	Combined Static and Motion Features for Deep-Networks-Based Activity Recognition in Videos. IEEE Trans. Circuits Syst. Video Technol. Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
2019	J	`jnl`	Extending Multi-Object Tracking systems to better exploit appearance and 3D information. CoRR Kanchana Ranasinghe, Sahan Liyanaarachchi, Harsha Ranasinghe, Mayuka Jayawardhana
2018	J	`jnl`	Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos. CoRR Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
2017	Misc	`conf`	Micro Actions and Deep Static Features for Activity Recognition. DICTA Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual