Search Results for author:
Found 20 papers, 14 papers with code
Explaining reviews and ratings with PACO: Poisson Additive Co-Clustering
With this novel technique we propose a new Bayesian model for joint collaborative filtering of ratings and text reviews through a sum of simple co-clusterings.
Recurrent Recommender Networks
Recommender systems traditionally assume that user profiles and movie attributes are static.
Spectral Methods for Nonparametric Models
Nonparametric models are versatile, albeit computationally expensive, tool for modeling mixture models.
Sampling Matters in Deep Embedding Learning
In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions.
Ranked #5 on
Image Retrieval
on CARS196
Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization
We consider the popular problem of sparse empirical risk minimization with linear predictors and a large number of both features and observations.
Compressed Video Action Recognition
), we propose to train a deep network directly on the compressed video.
Ranked #46 on
Action Classification
on Charades
(using extra training data)
Video Compression through Image Interpolation
An ever increasing amount of our digital communication, media consumption, and content creation revolves around videos.
Long-Term Feature Banks for Detailed Video Understanding
To understand the world, we humans constantly need to relate the present to the past, and put events in context.
Ranked #4 on
Egocentric Activity Recognition
on EPIC-KITCHENS-55
Fashion++: Minimal Edits for Outfit Improvement
We introduce Fashion++, an approach that proposes minimal adjustments to a full-body clothing outfit that will have maximal impact on its fashionability.
A Multigrid Method for Efficiently Training Video Models
We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pre-training, 128 GPUs or 1 GPU).
Ranked #1 on
Video Classification
on Kinetics
Lossless Image Compression through Super-Resolution
We introduce a simple and efficient lossless image compression algorithm.
Memory Optimization for Deep Networks
Deep learning is slowly, but steadily, hitting a memory bottleneck.
Towards Long-Form Video Understanding
Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds.
Ranked #26 on
Action Recognition
on AVA v2.2
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection.
Ranked #1 on
Action Classification
on Kinetics-600
(GFLOPs metric)
Masked Feature Prediction for Self-Supervised Visual Pre-Training
We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models.
Ranked #8 on
Action Recognition
on AVA v2.2
(using extra training data)
A ConvNet for the 2020s
The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model.
Ranked #1 on
Classification
on InDL
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
Instead of trying to process more frames at once like most existing methods, we propose to process videos in an online fashion and cache "memory" at each iteration.
Ranked #3 on
Action Anticipation
on EPIC-KITCHENS-100
(using extra training data)
Multiview Compressive Coding for 3D Reconstruction
We introduce a simple framework that operates on 3D points of single objects or whole scenes coupled with category-agnostic large-scale training from diverse RGB-D videos.
Reversible Vision Transformers
Reversible Vision Transformers achieve a reduced memory footprint of up to 15. 5x at roughly identical model complexity, parameters and accuracy, demonstrating the promise of reversible vision transformers as an efficient backbone for hardware resource limited training regimes.
PointInfinity: Resolution-Invariant Point Diffusion Models
We present PointInfinity, an efficient family of point cloud diffusion models.
