Search Results for author:
Found 51 papers, 22 papers with code
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition
MIFS compensates for information lost from using differential operators by recapturing information at coarse scales.
Long-short Term Motion Feature for Action Classification and Retrieval
Therefore, they need to occur frequently enough in the videos and to be be able to tell the difference among different types of motions.
The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition
First, we propose a two-stream Stacked Convolutional Independent Subspace Analysis (ConvISA) architecture to show that unsupervised learning methods can significantly boost the performance of traditional local features extracted from data-independent models.
Handcrafted Local Features are Convolutional Neural Networks
We approach this problem by first showing that local handcrafted features and Convolutional Neural Networks (CNNs) share the same convolution-pooling network structure.
Strategies for Searching Video Content with Text Queries or Video Examples
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing
We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees.
The Second Order Linear Model
We show that the conventional gradient descent heuristic is biased by the skewness of the distribution therefore is no longer the best practice of learning the SLM.
Nonconvex One-bit Single-label Multi-label Learning
We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels.
Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis
However, the development of a robust and reliable deep learning model for computer-aided diagnosis is still highly challenging due to the combination of the high heterogeneity in the medical images and the relative lack of training samples.
Which Factorization Machine Modeling is Better: A Theoretical Answer with Optimal Guarantee
This bound is sub-optimal comparing to the information theoretical lower bound $\mathcal{O}(kd)$.
Robust Gaussian Process Regression for Real-Time High Precision GPS Signal Enhancement
We validate the superiority of the proposed method in our real-time high precision positioning system against several popular state-of-the-art robust regression methods.
Differentiable Cloth Simulation for Inverse Problems
We propose a differentiable cloth simulator that can be embedded as a layer in deep neural networks.
Knapsack Pruning with Inner Distillation
Through this we produce compact architectures with the same FLOPs as EfficientNet-B0 and MobileNetV3 but with higher accuracy, by $1\%$ and $0. 3\%$ respectively on ImageNet, and faster runtime on GPU.
Ranked #3 on
Network Pruning
on ImageNet
Neural Architecture Design for GPU-Efficient Networks
To address this issue, we propose a general principle for designing GPU-efficient networks based on extensive empirical studies.
Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation
Simulation data can be utilized to extend real-world driving data in order to cover edge cases, such as vehicle accidents.
WeMix: How to Better Utilize Data Augmentation
To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation.
Robust Finite Mixture Regression for Heterogeneous Targets
FMR is an effective scheme for handling sample heterogeneity, where a single regression model is not enough for capturing the complexities of the conditional distribution of the observed samples given the features.
Learning Accurate Entropy Model with Global Reference for Image Compression
In this work, we propose a novel Global Reference Model for image compression to effectively leverage both the local and the global context information, leading to an enhanced compression rate.
Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition
To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures.
Neural Architecture Search
Vocal Bursts Intensity Prediction
Driving through the Lens: Improving Generalization of Learning-based Steering using Simulated Adversarial Examples
To ensure the wide adoption and safety of autonomous driving, the vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments.
Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet.
Ranked #2 on
Neural Architecture Search
on ImageNet
Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving
Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with unusual image properties.
KVT: k-NN Attention for Boosting Vision Transformers
A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies.
Fine-Grained AutoAugmentation for Multi-Label Classification
Data augmentation is a commonly used approach to improving the generalization of deep learning models.
ZenDet: Revisiting Efficient Object Detection Backbones from Zero-Shot Neural Architecture Search
Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS).
NAS-Bench-Zero: A Large Scale Dataset for Understanding Zero-Shot Neural Architecture Search
Based on these new discoveries, we propose i) a novel hybrid zero-shot proxy which outperforms existing ones by a large margin and is transferable among popular search spaces; ii) a new index for better measuring the true performance of ZS-NAS proxies in constrained NAS.
Hierarchical Cross Contrastive Learning of Visual Representations
In this work, we propose a novel approach termed Hierarchical Cross Contrastive Learning(HCCL) to further distill the information mismatched by the conventional contrastive loss.
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS).
Ranked #88 on
Object Detection
on COCO minival
Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering
We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving.
Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space
In Ada-NETS, each face is transformed to a new structure space, obtaining robust features by considering face features of the neighbour images.
GiraffeDet: A Heavy-Neck Paradigm for Object Detection
This heavy-backbone design paradigm is mostly due to the historical legacy when transferring image recognition models to object detection rather than an end-to-end optimized design for object detection.
Entroformer: A Transformer-based Entropy Model for Learned Image Compression
One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules.
FAR: Fourier Aerial Video Recognition
Our formulation uses a novel Fourier object disentanglement method to innately separate out the human agent (which is typically small) from the background.
Ranked #1 on
Action Recognition
on UAV Human
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition
We build a differentiable static-dynamic frequency mask prior to model the salient static and dynamic pixels in the video, crucial for the underlying task of action recognition.
Robust Graph Structure Learning via Multiple Statistical Tests
A natural way to construct a graph among images is to treat each image as a node and assign pairwise image similarities as weights to corresponding edges.
Differentiable Analog Quantum Computing for Optimization and Control
We formulate the first differentiable analog quantum computing framework with a specific parameterization design at the analog signal (pulse) level to better exploit near-term quantum devices via variational methods.
Entropy-Driven Mixed-Precision Quantization for Deep Network Design
Deploying deep convolutional neural networks on Internet-of-Things (IoT) devices is challenging due to the limited computational resources, such as limited SRAM memory and Flash storage.
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning
However, the relation between these two losses is not clear.
DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
To this end, a novel framework termed Mathematical Architecture Design for Deep CNN (DeepMAD) is proposed to design high-performance CNN models in a principled way.
Ranked #1 on
Neural Architecture Search
on ImageNet
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
In this work, we propose to automatically design efficient 3D CNN architectures via a novel training-free neural architecture search approach tailored for 3D CNNs considering the model complexity.
Ranked #84 on
Action Recognition
on Something-Something V2
PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
In this work, we aim to identify parameters characterizing a physical system from a set of multi-view videos without any assumption on object geometry or topology.
Making Vision Transformers Efficient from A Token Sparsification View
In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks.
Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models
Aerial Diffusion leverages a pretrained text-image diffusion model for prior knowledge.
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities
Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process.
ICAR: Image-based Complementary Auto Reasoning
Based on this notion, we propose a compatibility learning framework, a category-aware Flexible Bidirectional Transformer (FBT), for visual "scene-based set compatibility reasoning" with the cross-domain visual similarity input and auto-regressive complementary item generation.
HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
It seamlessly blends the visual features from the input image within a pretrained text-to-2Dimage stable diffusion model with a test-time optimization process for a careful bias-variance trade-off, which uses an Inverse Perspective Mapping (IPM) homography transformation to provide subtle cues for aerialview synthesis.
HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors
We demonstrate that HandyPriors attains comparable or superior results in the pose estimation task, and that the differentiable physics module can predict contact information for pose refinement.
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
Recent works show that 8-bit or lower weight quantization is feasible with minimal impact on end-to-end task performance, while the activation is still not quantized.
VLAP: Efficient Video-Language Alignment via Frame Prompting and Distilling for Video Question Answering
Our VLAP model addresses both efficient frame sampling and effective cross-modal alignment in a unified way.
Ranked #1 on
Video Question Answering
on STAR Benchmark
SHARE: Single-view Human Adversarial REconstruction
We perform a comprehensive analysis on the impact of camera poses on HPS reconstruction outcomes.
Merino: Entropy-driven Design for Generative Language Models on IoT Devices
Generative Large Language Models (LLMs) stand as a revolutionary advancement in the modern era of artificial intelligence (AI).
