Search Results for author:
Found 31 papers, 13 papers with code
Multiview Transformers for Video Recognition
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations.
Ranked #5 on
Action Recognition
on EPIC-KITCHENS-100
(using extra training data)
UnLoc: A Unified Framework for Video Localization Tasks
While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task.
Ranked #1 on
Action Segmentation
on COIN
Streaming Dense Video Captioning
An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video.
Improve Unsupervised Domain Adaptation with Mixup Training
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain.
Ranked #49 on
Domain Generalization
on PACS
Efficient Large Language Models: A Survey
Large Language Models (LLMs) have demonstrated remarkable capabilities in important tasks such as natural language understanding, language generation, and complex reasoning and have the potential to make a substantial impact on our society.
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime.
Deep AutoAugment
In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA).
Ranked #2 on
Data Augmentation
on ImageNet
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize architecture search on such representations which incurs search bias.
Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
In this paper, we propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance that is competitive to ANNs yet with low latency.
Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks
In particular, our method achieves state-of-the-art accuracy on ImageNet, while the memory cost and training time are reduced by more than 70% and 50%, respectively, compared with BPTT.
CATE: Computation-aware Neural Architecture Encoding with Transformers
Our experiments show that CATE is beneficial to the downstream search, especially in the large search space.
Ranked #15 on
Neural Architecture Search
on CIFAR-10
NAS-Bench-x11 and the Power of Learning Curves
While early research in neural architecture search (NAS) required extreme computational resources, the recent releases of tabular and surrogate benchmarks have greatly increased the speed and reproducibility of NAS research.
Soft Augmentation for Image Classification
We draw inspiration from human visual classification studies and propose generalizing augmentation with invariant transforms to soft augmentation where the learning target softens non-linearly as a function of the degree of the transform applied to the sample: e. g., more aggressive image crop augmentations produce less confident learning targets.
Learning Low-shot facial representations via 2D warping
In this work, we mainly study the influence of the 2D warping module for one-shot face recognition.
Word-based Domain Adaptation for Neural Machine Translation
Pre-training a model with word weights improves fine-tuning up to 1. 24% BLEU absolute and 1. 64% TER, respectively.
HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.
Unsupervised Visual Representation Learning with Increasing Object Shape Bias
(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance.
Image Retrieval for Structure-from-Motion via Graph Convolutional Network
Conventional image retrieval techniques for Structure-from-Motion (SfM) suffer from the limit of effectively recognizing repetitive patterns and cannot guarantee to create just enough match pairs with high precision and high recall.
Deep Learning in the Era of Edge Computing: Challenges and Opportunities
The era of edge computing has arrived.
The Twelvefold Way of Non-Sequential Lossless Compression
Many information sources are not just sequences of distinguishable symbols but rather have invariances governed by alternative counting paradigms such as permutations, combinations, and partitions.
Information Theory Information Theory
Quantifying the Temperature of Heated Microdevices UsingScanning Thermal Probes
Quantifying the temperature of microdevices is critical for probing nanoscale energy transport. Such quantification is often accomplished by integrating resistance thermometers into microdevices.
Mesoscale and Nanoscale Physics
FairFed: Enabling Group Fairness in Federated Learning
Training ML models which are fair across different demographic groups is of critical importance due to the increased integration of ML in crucial decision-making scenarios such as healthcare and recruitment.
VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
We explore an efficient approach to establish a foundational video-text model.
Ranked #1 on
Video Captioning
on ActivityNet Captions
(using extra training data)
Render-and-Compare: Cross-View 6 DoF Localization from Noisy Prior
Despite the significant progress in 6-DoF visual localization, researchers are mostly driven by ground-level benchmarks.
Long-term Visual Localization with Mobile Sensors
Despite the remarkable advances in image matching and pose estimation, image-based localization of a camera in a temporally-varying outdoor environment is still a challenging problem due to huge appearance disparity between query and reference images caused by illumination, seasonal and structural changes.
AutoTaskFormer: Searching Vision Transformers for Multi-task Learning
Vision Transformers have shown great performance in single tasks such as classification and segmentation.
Deep Active Contours for Real-time 6-DoF Object Tracking
Specifically, given an initial pose, we project the object model to the image plane to obtain the initial contour and use a lightweight network to predict how the contour should move to match the true object boundary, which provides the gradients to optimize the object pose.
Pixel Aligned Language Models
When taking locations as inputs, the model performs location-conditioned captioning, which generates captions for the indicated object or region.
UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization
Despite significant progress in global localization of Unmanned Aerial Vehicles (UAVs) in GPS-denied environments, existing methods remain constrained by the availability of datasets.
PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter
Our research undertakes a thorough exploration of the state-of-the-art perceiver resampler architecture and builds a strong baseline.
VideoPrism: A Foundational Visual Encoder for Video Understanding
We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model.
