Search Results for author:
Found 25 papers, 14 papers with code
Grafting Vision Transformers
In this paper, we present a simple and efficient add-on component (termed GrafT) that considers global dependencies and multi-scale information throughout the network, in both high- and low-resolution features alike.
Augmentation Learning for Semi-Supervised Classification
As the accuracy for ImageNet and similar datasets increased over time, the performance on tasks beyond the classification of natural images is yet to be explored.
Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines.
Temporal Relevance Analysis for Video Action Models
In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature.
CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection
Single-particle cryo-electron microscopy (cryo-EM) has become one of the mainstream structural biology techniques because of its ability to determine high-resolution structures of dynamic bio-molecules.
Generating Realistic Physical Adversarial Examplesby Patch Transformer Network
Physical adversarial attacks apply carefully crafted adversarial perturbations onto real objects to maliciously alter the prediction of object classifiers or detectors.
Can An Image Classifier Suffice For Action Recognition?
We explore a new perspective on video understanding by casting the video recognition problem as an image recognition task.
RegionViT: Regional-to-Local Attention for Vision Transformers
The regional-to-local attention includes two steps: first, the regional self-attention extract global information among all regional tokens and then the local self-attention exchanges the information among one regional token and the associated local tokens via self-attention.
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
Specifically, given a video segment, a multi-modal policy network is used to decide what modalities should be used for processing by the recognition model, with the goal of improving both accuracy and efficiency.
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
To this end, we propose a dual-branch transformer to combine image patches (i. e., tokens in a transformer) of different sizes to produce stronger image features.
Ranked #398 on
Image Classification
on ImageNet
Generating Adversarial Computer Programs using Optimized Obfuscations
We further show that our formulation is better at training models that are robust to adversarial attacks.
Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition
In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets.
More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation
Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets.
Ranked #72 on
Action Recognition
on Something-Something V2
(using extra training data)
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding
Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds.
Adversarial T-shirt! Evading Person Detectors in A Physical World
To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to-rigid objects such as T-shirts.
Reasoning About Human-Object Interactions Through Dual Attention Networks
The model not only finds when an action is happening and which object is being manipulated, but also identifies which part of the object is being interacted with.
Interpreting Adversarial Examples by Activation Promotion and Suppression
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers.
Efficient Fusion of Sparse and Complementary Convolutions
We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions.
Structured Adversarial Attack: Towards General Implementation and Better Interpretability
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example.
Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks, using popular architectures including ResNet and ResNeXt.
Moments in Time Dataset: one million videos for event understanding
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds.
Sparse-Complementary Convolution for Efficient Model Utilization on CNNs
By simply replacing the convolution of a CNN with our sparse-complementary convolution, at the same FLOPs and parameters, we can improve top-1 accuracy on ImageNet by 0. 33% and 0. 18% for ResNet-101 and ResNet-152, respectively.
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.
Ranked #20 on
Face Detection
on WIDER Face (Hard)
Random Laplace Feature Maps for Semigroup Kernels on Histograms
With the goal of accelerating the training and testing complexity of nonlinear kernel methods, several recent papers have proposed explicit embeddings of the input data into low-dimensional feature spaces, where fast linear methods can instead be used to generate approximate solutions.
Temporal Sequence Modeling for Video Event Detection
Based on this idea, we represent a video by a sequence of visual words learnt from the video, and apply the Sequence Memoizer [21] to capture long-range dependencies in a temporal context in the visual sequence.
