Greg Mori (original) (raw)

Mengyao Zhai successfully defended her Ph.D. thesis Towards Lifelong Learning for Generative Adversarial Networks. Congratulations Mengyao!

Mohammad Hadi Salari successfully defended his M.Sc. thesis Kronecker-factored Hessian Approximation for Continual Learning. Congratulations Hadi!

Hamed Shirzad successfully defended his M.Sc. thesis Graph Generation Using Tree Decomposition. Congratulations Hamed!

Mengyao Zhai (PhD) and Lei Chen (PhD) had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2021. A lifelong learning approach for conditional image generation is presented.

Xiaobin Chang (PDF) had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2021. Discriminative prototypes are learned for dynamic time warping based sequence matching.

Sha Hu (PhD) had a paper accepted to International Conference on Robotics and Automation (ICRA), 2021. Multi-fidelity Bayesian optimization is used to efficiently search for robot designs using simpler tasks and fewer epochs of learning.

Nazanin Mehrasa successfully defended her Ph.D. thesis Towards Event Analysis in Time-series Data: Asynchronous Probabilistic Models and Learning from Partial Labels.. Congratulations Nazanin!

Yu Gong (PhD) had a paper accepted to International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. A variational autoencoder modeling masks for data imputation is presented.

Ruizhi Deng (PhD) had a paper accepted to Neural Information Processing Systems (NeurIPS), 2020. A normalizing flow model for time series data is presented.

Srikanth Muralidharan successfully defended his Ph.D. thesis Multi-person Video Understanding with Deep Neural Networks. Congratulations Srikanth!

Mengyao Zhai (PhD), Lei Chen, Fred Tung (PDF), Jiawei He (PhD), and Megha Nawhal (PhD) had a paper accepted to European Conference on Computer Vision (ECCV), 2020. PiggybackGAN, a lifelong learning framework with filter reuse for image generation is presented.

Megha Nawhal (PhD) and Mengyao Zhai (PhD) had a paper accepted to European Conference on Computer Vision (ECCV), 2020. Zero-shot generation of human-object interaction videos is achieved via a novel graph-based GAN discriminator.

Sha Hu (PhD) had a paper accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020. Strategies for crowd navigation are learned from graph-based representations of people.

Jiawei He successfully defended his Ph.D. thesis Theoretical and Applicational Advances in Variational Autoencoders. Congratulations Jiawei!

Zhiwei Deng successfully defended his Ph.D. thesis Learning Deep Structured Models for Visual Understanding. Congratulations Zhiwei!

Yu Gong successfully defended his M.Sc. thesis Latent Structure Learning in Variational Autoencoders. Congratulations Yu!

Akash Abdu Jyothi (PhD), Thibaut Durand (PDF), and Jiawei He (PhD) had a paper accepted to IEEE/CVF International Conference on Computer Vision (ICCV), 2019. A VAE model for counts and layouts of objects in scenes, capable of capturing diverse quantities and arrangements for image generation.

Mengyao Zhai (PhD), Lei Chen, Fred Tung (PDF), Jiawei He (PhD), and Megha Nawhal (PhD) had a paper accepted to IEEE/CVF International Conference on Computer Vision (ICCV), 2019. A framework for continual learning of conditional generation, alleviating the need for maintaining input conditions as well as desired output.

Fred Tung (PDF) had a paper accepted to IEEE/CVF International Conference on Computer Vision (ICCV), 2019. Knowledge distillation between student and teacher neural networks by maintaining *similarities* of activations among semantically related training examples, rather than the standard mimicking of actual outputs.

Ruizhi Deng successfully defended his M.Sc. thesis Adaptive Appearance Rendering. Congratulations Ruizhi!

Jiawei He (PhD) and Yu Gong had a paper accepted to the International Conference on Learning Representations, 2019. A method for learning latent dependency structures in VAEs is developed.

Nazanin Mehrasa (PhD), Akash Abdu Jyothi (PhD), Thibaut Durand (PDF), and Jiawei He had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2019. The paper develops a novel variational autoencoder model for point process time series data.

Thibaut Durand (PDF) and Nazanin Mehrasa (PhD) had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2019. Learning classifiers from partial annotations is explored in this work.

Yifang Fu successfully defended her M.Sc. thesis_Deep Video Visual Relation Detection_. Congratulations Yifang!

Jiawei He (PhD) had a paper accepted to the Symposium on Advances in Approximate Bayesian Inference (at NeurIPS), 2018. The paper describes a semantic prior for image generation.

Mostafa S. Ibrahim successfully defended his Ph.D. thesis_Deep Models for Multi-Person Activity Understanding_. Congratulations Mostafa!

Zhiwei Deng (PhD),Jiacheng Chen (BSc), and Yifang Fu (MSc) had a paper accepted to Neural Information Processing Systems (NeurIPS), 2018. A programmatic approach to constructing priors for VAE-based generative models for complex scenes is proposed.

Jiawei He (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A temporal variational auto-encoder for synthesizing controllable sequences of human motion is presented.

Changan Chen (BSc) and Fred Tung (PDF) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A deep network compression algorithm for meeting operational performance constraints is presented.

Ruizhi Deng (MSc) andZhiwei Deng (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A sparse aggregation approach for deep neural networks is proposed and analyzed.

Fabien Baradel (visiting PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. An object reasoning approach to video understanding is presented.

Moustafa S. Ibrahim (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A relational neural network layer for supervised and unsupervised learning of human-contextual feature learning for group activity recognition is presented.

Mengyao Zhai (PhD),Ruizhi Deng (MSc),Jiacheng Chen (BSc),Lei Chen (PhD) and Zhiwei Deng (PhD) had a paper accepted to the British Machine Vision Conference (BMVC), 2018. An adaptive rendering approach for generating images of human action is developed.

Fred Tung (PDF) had a paper accepted to IEEE Computer Vision and Pattern Recognition (CVPR), 2018. Deep network weight pruning and quantization are learned in parallel with training.