349 citations · 2.5k across the 74 of their papers we have counts for
14 papers · 1 filter
Graph Convolutional Module for Temporal Action Localization in Videos
Runhao Zeng, Wenbing Huang, Mingkui Tan +4
Temporal action localization has long been researched in computer vision. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e.,…
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
Lijie Fan, Sijia Liu, Pin-Yu Chen +2
Contrastive learning (CL) can learn generalizable feature representations and achieve the state-of-the-art performance of downstream tasks by finetuning a linear classifier on top…
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
Ji Lin, Wei-Ming Chen, Han Cai +2
Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in…
Network Augmentation for Tiny Deep Learning
Han Cai, Chuang Gan, Ji Lin +1
We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation…
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device
Ji Lin, Chuang Gan, Kuan Wang +1
The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture te…
Self-supervised Audiovisual Representation Learning for Remote Sensing Data
Konrad Heidler, Lichao Mou, Di Hu +5
Many current deep learning approaches make extensive use of backbone networks pre-trained on large datasets like ImageNet, which are then fine-tuned to perform a certain task. In r…
Certifiably Robust Interpretation via Renyi Differential Privacy
Ao Liu, Xiaoyu Chen, Sijia Liu +2
Motivated by the recent discovery that the interpretation maps of CNNs could easily be manipulated by adversarial attacks against network interpretability, we study the problem of…
Global Rhythm Style Transfer Without Text Transcriptions
Kaizhi Qian, Yang Zhang, Shiyu Chang +4
Prosody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody…
Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
Shaobo Min, Qi Dai, Hongtao Xie +3
Cross-modal correlation provides an inherent supervision for video unsupervised representation learning. Existing methods focus on distinguishing different video clips by visual an…
Curious Representation Learning for Embodied Intelligence
Yilun Du, Chuang Gan, Phillip Isola
Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numer…
TransCenter: Transformers with Dense Representations for Multiple-Object Tracking
Yihong Xu, Yutong Ban, Guillaume Delorme +3
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks…
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Ren Wang, Kaidi Xu, Sijia Liu +4
Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. It enables us to learn a meta-initialization} of model…
AGENT: A Benchmark for Core Psychological Reasoning
Tianmin Shu, Abhishek Bhandwaldar, Chuang Gan +6
For machine agents to successfully interact with humans in real-world settings, they will need to develop an understanding of human mental life. Intuitive psychology, the ability t…
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
Wenhao Wu, Dongliang He, Tianwei Lin +3
Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have…