The Computational Vision and Learning (CVL) Lab
Franz 3621C, Psychology Department, UCLA, Los Angeles, CA, 90095
The basic goal of our research is to investigate how humans learn and reason, and how intelligent machines might emulate them. In tasks that arise both in childhood (e.g., perceptual learning and language acquisition) and in adulthood (e.g., action understanding and analogical inference), humans often paradoxically succeed in making inferences from inadequate data. The data available are often sparse (very few examples), ambiguous (multiple possible interpretations), and noisy (low signal-to-noise ratio). How can an intelligent system cope?
We approach this basic question as it arises in both perception and higher cognition. Our research is highly interdisciplinary, integrating theories and methods from psychology, statistics, computer vision, machine learning, and computational neuroscience. The unified picture emerging from our work is that the power of human inference depends on two basic principles. First, people exploit generic priors — tacit general assumptions about the way the world works, which guide learning and inference from observed data. Second, people have a capacity to generate and manipulate structured representations— representations organized around distinct roles, such as multiple joints in motion with respect to one another in action perception. Our current areas of active study include action understanding, motion perception, object recognition, causal learning, and analogical reasoning. See the list of ongoing research projects on the research page.
Our research is generously funded by the National Science Foundation, ONR, AFOSR, and UCLA.
Lab News [news archive]
|2018. 02||Our lab and the UCLA reasoning lab received a Google faculty research grant to study analogy.|
|2017. 08||Our lab received a new NSF grant to study action perception and causal reasoning.|
|2017. 06||Hongjing received UCLA Psychology Teaching Award.|
|2017. 06||One of our CogSci papers entitled Inferring human interaction from motion trajectories in aerial videos won the computational modeling prize in perception/action from the Cognitive Science Society. Congratulations, Tianmin, Yujia and Lifeng!|
|2017. 05||Thanks to our lab members and collaborators, Yujia, Joseph, Nick, Greda, for doing a great job to present 4 posters and 1 talk at VSS. What a fun conference!|
|2017. 05||James Kubricht received the Dissertation Year Fellowship. Congratulations, James!|
|2017. 05||Pratyusha R. Javagula, Aya Strauss, and Tabby Safar presented their research project in the undergraduate research PURC conference.|
|2017. 04||Yujia received the 2017 Liu Yunghuo Bei Qui Memorial Fellowship. Congratulations, Yujia!|
|2016. 04||Tabby Safari, the undergraduate RA with Joseph, will present their research project in the PURC conference.|
|2016. 04||Yujia received the Yong Scientist Travel Award from the Cognitive Science Society. Congratulations, Yujia!|
|2016. 03||2 talk and 2 poster presentations accepted at VSS. (1) Lu; (2) Peng & Lu; (3) Thurman & Lu; (4) Su & Lu.|