Abhinav Gupta Homepage

Abhinav Gupta

Assistant Research Professor The Robotics Institute School of Computer Science Carnegie Mellon University

Office:   EDSH 213
Phone:   412-268-2067
Email :   abhinavg [at] cs [dot] cmu [dot] edu

I am an Assistant Research Professor at Carnegie Mellon University. Prior to this, I was a post-doctoral fellow here working with Alyosha Efros and Martial Hebert. Before coming to Pittsburgh, I was working with Larry Davis at UMD and Jianbo Shi at UPenn. My PhD thesis was on "Beyond Nouns and Verbs".

Research Interests

My research interest include:

How do we represent the visual world ? My research focuses on developing representation and reasoning approaches for deeper understanding of the scene. I am interested in formulating the scene understanding problem in terms of the underlying 3D scene and develop reasoning approaches based on physical, functional and causal relationships between the different elements in the scene. The key idea is to have a qualitative representation and yet have a meaningful grounding in the physical scene.

What is the link between Language and Vision ? What role does language play in visual learning? I am interested in exploring how declarative information and other linguistic information can be harnessed to efficiently learn how the world works (structural information). I am also interesting in exploring how we can obtain such linguistic information.

How are actions and objects related to each other? I have been focusing on studying how do humans interact with their environment and how does their perception of visual world depends on these interactions and their abilities. Building upon Gibson's idea of affordances, we have recently proposed the concept of human centric scene understanding.

Students

David Fouhey (Robotics PhD, co-advised with M. Hebert)
Abhinav Shrivastava (Robotics PhD, co-advised with A. Efros and M. Hebert)
Xinlei Chen (LTI PhD)
Jacob Walker (Robotics PhD, co-advised with M. Hebert)

Former Students and Collaborators

Tomasz Malisiewicz (now Postdoc at MIT)
Saurabh Singh (Robotics MS, now PhD Student at UIUC)

Courses

16-824 Learning-Based Methods in Vision (Fall 2013)

Selected Projects
(Please see Publications for a complete list)
(Please see Downloads for code and datasets)

	Arpit Jain, Abhinav Gupta, Mikel Rodriguez and Larry S. Davis. Representing Videos using Mid-level Discriminative Patches. In CVPR 2013.
	David Fouhey, Vincent Delaitre, Abhinav Gupta, Alexei A. Efros, Ivan Laptev, Josef Sivic. People Watching: Human Actions as a Cue for Single View Geometry. In ECCV 2012.(Oral)
	Abhinav Shrivastava, Saurabh Singh, Abhinav Gupta.Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes. In ECCV 2012.(Oral)
	Saurabh Singh, Abhinav Gupta, Alexei A. Efros. Unsupervised Discovery of Mid-Level Discriminative Patches. In ECCV 2012.
	Vincent Delaitre, David Fouhey, Ivan Laptev, Josef Sivic Abhinav Gupta, Alexei A. Efros. Scene Semantics from Long-term Observation of People. In ECCV 2012.
	Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros. What makes Paris look like Paris? In SIGGRAPH 2012. (Oral)
	Abhinav Shrivastava, Tomasz Malisiewicz, Abhinav Gupta, Alexei A. Efros, Data-driven Visual Similarity for Cross-domain Image Matching, In SIGGRAPH Asia 2011

	Tomasz Malisiewicz, Abhinav Gupta, Alexei A. Efros, Ensemble of Exemplar-SVMs for Object Detection and Beyond, In ICCV 2011. Source code (beta version) available

	Abhinav Gupta, Scott Satkin, Alexei A. Efros and M. Hebert, From 3D Scene Geometry to Human Workspace. In CVPR 2011. (Oral) Source code partly available

	David C. Lee, Abhinav Gupta, Martial Hebert, and Takeo Kanade, Estimating Spatial Layout of Rooms using Volumetric Reasoning about Objects and Surfaces, In NIPS 2010. Source code available

	Abhinav Gupta, Alexei A. Efros and M. Hebert, Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics. In ECCV 2010. (Oral) (Best Paper Runner Up Award) Featured in Science Daily and ZD Net. Source code available

	Behjat Siddiquie and Abhinav Gupta, Beyond Active Noun Tagging: Modeling Contextual Interactions for Multi-Class Active Learning, In CVPR 2010. (Oral)

	Abhinav Gupta, Praveen Srinivasan, Jianbo Shi and Larry S. Davis, Understanding Videos, Constructing Plots: Learning a Visually Grounded Storyline Model from Annotated Videos, In CVPR 2009. (Oral) Featured in an IEEE Spectrum and Discovery article. Also covered in Ethiopian Review and SiliconIndia.

	Abhinav Gupta and Larry S. Davis, Beyond Nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers, In ECCV 2008 (Oral)

	Abhinav Gupta, Aniruddha Kembhavi and Larry S. Davis, Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition, In Trans. on PAMI (Special Issue on Probabilistic Graphical Models). Downloads Available: Dataset Abhinav Gupta and Larry S. Davis, Objects in Action: An Approach for Combining Action Understanding and Object Perception, In CVPR 2007 Downloads Available: Dataset

	Abhinav Gupta, Jianbo Shi and Larry S. Davis, A “Shape Aware” Model for semi-supervised Learning of Objects and its Context, In NIPS 2008 (Spotlight Poster)

Funding Sources

Office of Naval Research
IARPA
Google