334 citations · 883 across the 97 of their papers we have counts for
7 papers · 1 filter
Scalable Model Compression by Entropy Penalized Reparameterization
Deniz Oktay, Johannes Ballé, Saurabh Singh +1
We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to…
Relational Action Forecasting
Chen Sun, Abhinav Shrivastava, Carl Vondrick +3
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future acti…
Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completion
Tao Hu, Zhizhong Han, Abhinav Shrivastava +1
We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or…
EvalNorm: Estimating Batch Normalization Statistics for Evaluation
Saurabh Singh, Abhinav Shrivastava
Batch normalization (BN) has been very effective for deep learning and is widely used. However, when training with small minibatches, models using BN exhibit a significant degradat…
Detecting Human-Object Interactions via Functional Generalization
Ankan Bansal, Sai Saketh Rambhatla, Abhinav Shrivastava +1
We present an approach for detecting human-object interactions (HOIs) in images, based on the idea that humans interact with functionally similar objects in a similar manner. The p…
Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
Ahmed Taha, Yi-Ting Chen, Teruhisa Misu +2
We introduce an unsupervised formulation to estimate heteroscedastic uncertainty in retrieval systems. We propose an extension to triplet loss that models data uncertainty for each…
Boosting Standard Classification Architectures Through a Ranking Regularizer
Ahmed Taha, Yi-Ting Chen, Teruhisa Misu +2
We employ triplet loss as a feature embedding regularizer to boost classification performance. Standard architectures, like ResNet and Inception, are extended to support both losse…