• Publications
  • Influence
Learning to Adapt Structured Output Space for Semantic Segmentation
TLDR
A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality. Expand
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
TLDR
The proposed Deep Stochastic IOC RNN Encoder-decoder framework, DESIRE, for the task of future predictions of multiple interacting agents in dynamic scenes significantly improves the prediction accuracy compared to other baseline methods. Expand
Person Re-identification in the Wild
TLDR
A new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, and it is shown that pedestrian detection aids re-ID through two simple yet effective improvements: a cascaded fine-tuning strategy that trains a detection model first and then the classification model, and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Expand
Towards Large-Pose Face Frontalization in the Wild
TLDR
This work proposes a novel deep 3D Morphable Model (3DMM) conditioned Face Frontalization Generative Adversarial Network (GAN), termed as FF-GAN, to generate neutral head pose face images, which differs from both traditional GANs and 3DMM based modeling. Expand
Universal Correspondence Network
TLDR
A convolutional spatial transformer to mimic patch normalization in traditional features like SIFT is proposed, which is shown to dramatically boost accuracy for semantic correspondences across intra-class shape variations. Expand
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
TLDR
This work proposes DS, a novel dataset for road scene understanding in unstructured environments where the above assumptions are largely not satisfied, and proposes a new four-level label hierarchy, which allows varying degrees of complexity and opens up possibilities for new training methods. Expand
Learning Efficient Object Detection Models with Knowledge Distillation
TLDR
This work proposes a new framework to learn compact and fast object detection networks with improved accuracy using knowledge distillation and hint learning and shows consistent improvement in accuracy-speed trade-offs for modern multi-class detection models. Expand
Domain Adaptation for Structured Output via Discriminative Patch Representations
TLDR
A domain adaptation method to adapt the source data to the unlabeled target domain by discovering multiple modes of patch-wise output distribution through the construction of a clustered space and using an adversarial learning scheme to push the feature representations of target patches in the clustered space closer to the distributions of source patches. Expand
Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving
TLDR
This paper presents a real-time monocular SFM system that corrects for scale drift using a novel cue combination framework for ground plane estimation, yielding accuracy comparable to stereo over long driving sequences. Expand
A 4D Light-Field Dataset and CNN Architectures for Material Recognition
TLDR
A new light-field dataset of materials is introduced, and the best performing CNN architecture achieves a 7 % boost compared with 2D image classification, which constitute important baselines that can spur further research in the use of CNNs for light- field applications. Expand
...
1
2
3
4
5
...