• Publications
  • Influence
Frustum PointNets for 3D Object Detection from RGB-D Data
TLDR
This work directly operates on raw point clouds by popping up RGBD scans and leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects.
Semi-Supervised Nonlinear Hashing Using Bootstrap Sequential Projection Learning
TLDR
This paper proposes a semi-supervised nonlinear hashing algorithm using bootstrap sequential projection learning which effectively corrects the errors by taking into account of all the previous learned bits holistically without incurring the extra computational overhead.
Watch-n-patch: Unsupervised understanding of actions and relations
TLDR
The model learns the high-level action co-occurrence and temporal relations between the actions in the activity video and is applied to unsupervised action segmentation and recognition, and also to a novel application that detects forgotten actions, which is called action patching.
Unsupervised face-name association via commute distance
TLDR
A novel framework named face- name association via commute distance (FACD), which judges face-name and face-null assignments under a unified framework via commutedistance (CD) algorithm, and a novel anchor-based commute Distance (ACD) algorithm whose main idea is using the anchor point representation structure to accelerate the eigen-decomposition of the adjacency matrix of a graph.
A content-based video copy detection method with randomly projected binary features
TLDR
A keyframe-based copy retrieval method that exhaustively searches the copy candidates from the large video database without indexing and an effective scoring and localization algorithm is proposed to further refine the retrieved copies and accurately locate the video segments.
Watch-n-Patch: Unsupervised Learning of Actions and Relations
TLDR
This work proposes a new probabilistic model that allows for long-range action relations that commonly exist in the composite activities, which is challenging in previous works.
Hierarchical Semantic Labeling for Task-Relevant RGB-D Perception
TLDR
This work presents an algorithm that produces hierarchical labelings of a scene, following is-part-of and is-type-of relationships, based on a Conditional Random Field that relates pixel-wise and pair-wise observations to labels.
Exploiting Location-Based Context for POI Recommendation When Traveling to a New Region
TLDR
This research presented New Place Recommendation Algorithm (N-PRA) which is designed based on Latent Factor model, and experimental results show that the algorithm presented in this paper could achieve a better accuracy.
A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition
TLDR
This work directly formulate the keypoint recognition as an image patch retrieval problem, which enjoys the merit of finding the matched keypoint and its pose simultaneously, and proposes a novel convolutional treelets approach to effectively extract the binary features from the patches.
...
...