• Publications
  • Influence
Cascade R-CNN: Delving Into High Quality Object Detection
A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset, and experiments show that it is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength.
Anomaly detection in crowded scenes
A novel framework for anomaly detection in crowded scenes is presented and the proposed representation is shown to outperform various state of the art anomaly detection techniques.
A new approach to cross-modal multimedia retrieval
It is shown that accounting for cross-modal correlations and semantic abstraction both improve retrieval accuracy and are shown to outperform state-of-the-art image retrieval systems on a unimodal retrieval task.
Privacy preserving crowd monitoring: Counting people without people models or tracking
We present a privacy-preserving system for estimating the size of inhomogeneous crowds, composed of pedestrians that travel in different directions, without using explicit object segmentation or
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi- scale object detection, which is learned end-to-end, by optimizing a multi-task loss.
Anomaly Detection and Localization in Crowded Scenes
The detection and localization of anomalous behaviors in crowded scenes is considered, and a joint detector of temporal and spatial anomalies is proposed. The proposed detector is based on a video
Supervised Learning of Semantic Classes for Image Annotation and Retrieval
The supervised formulation is shown to achieve higher accuracy than various previously published methods at a fraction of their computational cost and to be fairly robust to parameter tuning.
Cascade R-CNN: High Quality Object Detection and Instance Segmentation
A multi-stage object detection architecture, the Cascade R-CNN, composed of a sequence of detectors trained with increasing IoU thresholds, which significantly improves high-quality detection on generic and specific object datasets, including VOC, KITTI, CityPerson, and WiderFace.
Deep Learning with Low Precision by Half-Wave Gaussian Quantization
An half-wave Gaussian quantizer (HWGQ) is proposed for forward approximation and shown to have efficient implementation, by exploiting the statistics of of network activations and batch normalization operations, and to achieve much closer performance to full precision networks than previously available low-precision networks.
Bidirectional Learning for Domain Adaptation of Semantic Segmentation
A self-supervised learning algorithm to learn a better segmentation adaptation model and in return improve the image translation model and the bidirectional learning framework for domain adaptation of segmentation is proposed.