Research Area
Year Published

203 Results

October 27, 2019

Video Classification with Channel-Separated Convolutional Networks

International Conference on Computer Vision (ICCV)

This paper studies the effects of different design choices in 3D group convolutional networks for video classification. We empirically demonstrate that the amount of channel interactions plays an important role in the accuracy of 3D group convolutional networks.

By: Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli

October 27, 2019

Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment

International Conference on Computer Vision (ICCV)

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a “downstream” task to guide the process of phrase localization.

By: Samyak Datta, Karan Sikka, Anirban Roy, Karuna Ahuja, Devi Parikh, Ajay Divakaran

October 27, 2019

Order-Aware Generative Modeling Using the 3D-Craft Dataset

International Conference on Computer Vision (ICCV)

We introduce 3D-Craft, a new dataset of 2,500 Minecraft houses each built by human players sequentially from scratch. To learn from these human action sequences, we propose an order-aware 3D generative model called VoxelCNN.

By: Zhuoyuan Chen, Demi Guo, Tong Xiao, Saining Xie, Xinlei Chen, Haonan Yu, Jonathan Gray, Kavya Srinet, Haoqi Fan, Jerry Ma, Charles R. Qi, Shubham Tulsiani, Arthur Szlam, Larry Zitnick

October 27, 2019

DistInit: Learning Video Representations Without a Single Labeled Video

International Conference on Computer Vision (ICCV)

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models has not been able to keep up with the ever increasing depth and sophistication of these networks. In this work we propose an alternative approach to learning video representations that requires no semantically labeled videos, and instead leverages the years of effort in collecting and labeling large and clean still-image datasets.

By: Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan

October 27, 2019

Compositional Video Prediction

International Conference on Computer Vision (ICCV)

We present an approach for pixel-level future prediction given an input image of a scene. We observe that a scene is comprised of distinct entities that undergo motion and present an approach that operationalizes this insight. We implicitly predict future states of independent entities while reasoning about their interactions, and compose future video frames using these predicted states.

By: Yufei Ye, Maneesh Singh, Abhinav Gupta, Shubham Tulsiani

October 27, 2019

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Neural Information Processing Systems (NeurIPS)

Modern approaches for multi-person pose estimation in video require large amounts of dense annotations. However, labeling every frame in a video is costly and labor intensive. To reduce the need for dense annotations, we propose a PoseWarper network that leverages training videos with sparse annotations (every k frames) to learn to perform dense temporal pose propagation and estimation.

By: Gedas Bertasius, Christoph Feichtenhofer, Du Tran, Jianbo Shi, Lorenzo Torresani

October 27, 2019

Single-Network Whole-Body Pose Estimation

International Conference on Computer Vision (ICCV)

We present the first single-network approach for 2D whole-body pose estimation, which entails simultaneous localization of body, face, hands, and feet keypoints. Due to the bottom-up formulation, our method maintains constant real-time performance regardless of the number of people in the image.

By: Gines Hidalgo, Yaadhav Raaj, Haroon Idrees, Donglai Xiang, Hanbyul Joo, Tomas Simon, Yaser Sheikh

October 27, 2019

Canonical Surface Mapping via Geometric Cycle Consistency

International Conference on Computer Vision (ICCV)

We explore the task of Canonical Surface Mapping (CSM). Specifically, given an image, we learn to map pixels on the object to their corresponding locations on an abstract 3D model of the category.

By: Nilesh Kulkarni, Abhinav Gupta, Shubham Tulsiani

October 27, 2019

Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation

International Conference on Computer Vision (ICCV)

Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention. As data annotation requires massive human labor from experienced radiologists, it is common that training data are partially labeled, e.g., pancreas datasets only have the pancreas labeled while leaving the rest marked as background. However, these background labels can be misleading in multi-organ segmentation since the “background” usually contains some other organs of interest. To address the background ambiguity in these partially-labeled datasets, we propose Prior-aware Neural Network (PaNN) via explicitly incorporating anatomical priors on abdominal organ sizes, guiding the training process with domain-specific knowledge.

By: Yuyin Zhou, Zhe Li, Song Bai, Chong Wang, Xinlei Chen, Mei Han, Elliot Fishman, Alan Yuille

October 27, 2019

Improved Conditional VRNNs for Video Prediction

International Conference on Computer Vision (ICCV)

Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model multiple possible future outcomes, they have a tendency to produce blurry predictions. In this work we argue that this is a sign of underfitting.

By: Lluís Castrejón, Nicolas Ballas, Aaron Courville