Search Results for author:
Found 59 papers, 13 papers with code
Compact Generalized Non-local Network
The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos.
Inception Convolution with Efficient Dilation Search
To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them.
Ranked #59 on
Fine-Grained Image Classification
on Stanford Cars
Improving Auto-Augment via Augmentation-Wise Weight Sharing
On CIFAR-10, we achieve a top-1 error rate of 1. 24%, which is currently the best performing single model without extra training data.
GLiT: Neural Architecture Search for Global and Local Image Transformer
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.
Ranked #498 on
Image Classification
on ImageNet
DETR for Crowd Pedestrian Detection
Furthermore, the bipartite match of ED harms the training efficiency due to the large ground truth number in crowd scenes.
BN-NAS: Neural Architecture Search with Batch Normalization
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS).
Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment
Video quality assessment (VQA) aims to simulate the human perception of video quality, which is influenced by factors ranging from low-level color and texture details to high-level semantic content.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution
To enlarge RF with contained LUT sizes, we propose a novel Reconstructed Convolution(RC) module, which decouples channel-wise and spatial calculation.
Evolving Search Space for Neural Architecture Search
The automation of neural architecture design has been a coveted alternative to human experts.
Acoustic scene analysis with multi-head attention networks
Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns.
A Galaxy-Scale Fountain of Cold Molecular Gas Pumped by a Black Hole
The entire scenario is therefore consistent with a galaxy-spanning "fountain", wherein cold gas clouds drain into the black hole accretion reservoir, powering jets and bubbles that uplift a cooling plume of low-entropy multiphase gas, which may stimulate additional cooling and accretion as part of a self-regulating feedback loop.
Astrophysics of Galaxies
Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting
Finally, the max-pooling loss trained LSTM initialized with a cross-entropy pre-trained network shows the best performance, which yields $67. 6\%$ relative reduction compared to baseline feed-forward DNN in Area Under the Curve (AUC) measure.
An Empirical Evaluation of Zero Resource Acoustic Unit Discovery
Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations.
Generalized Canonical Correlation Analysis for Classification
For multiple multivariate data sets, we derive conditions under which Generalized Canonical Correlation Analysis (GCCA) improves classification performance of the projected datasets, compared to standard Canonical Correlation Analysis (CCA) using only two data sets.
Semi-supervised Acoustic Event Detection based on tri-training
This paper presents our work of training acoustic event detection (AED) models using unlabeled dataset.
Compression of Acoustic Event Detection Models with Low-rank Matrix Factorization and Quantization Training
In this paper, we present a compression approach based on the combination of low-rank matrix factorization and quantization training, to reduce complexity for neural network based acoustic event detection (AED) models.
Neural Text Normalization with Subword Units
We find subword models with additional linguistic features yield the best performance (with a word error rate of 0. 17{\%}).
AppDialogue: Multi-App Dialogues for Intelligent Assistants
Users will interact with an individual app on smart devices (e. g., phone, TV, car) to fulfill a specific goal (e. g. find a photographer), but users may also pursue more complex tasks that will span multiple domains and apps (e. g. plan a wedding ceremony).
Compression of Acoustic Event Detection Models With Quantized Distillation
Acoustic Event Detection (AED), aiming at detecting categories of events based on audio signals, has found application in many intelligent systems.
Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
With the combination of these two designs, an architecture transformation scheme could be discovered to adapt a network designed for image classification to task of object detection.
POD: Practical Object Detection with Scale-Sensitive Network
Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance.
Improving One-shot NAS by Suppressing the Posterior Fading
In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.
Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection
Instead of searching and constructing an entire network, NATS explores the architecture space on the base of existing network and reusing its weights.
Computation Reallocation for Object Detection
However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal.
Few-shot acoustic event detection via meta-learning
We study few-shot acoustic event detection (AED) in this paper.
Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
Training with more data has always been the most stable and effective way of improving performance in deep learning era.
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Specifically, the difficulties for architecture searching in such a complex space has been eliminated by the proposed stabilized share-parameter proxy, which employs Stochastic Gradient Langevin Dynamics to enable fast shared parameter sampling, so as to achieve stabilized measurement of architecture performance even in search space with complex topological structures.
Atacama Compact Array Measurements of the Molecular Mass in the NGC 5044 Cooling Flow Group
This indicates that the two giant molecular clouds seen in absorption are most likely within the sphere of influence of the supermassive black hole.
Astrophysics of Galaxies
On Front-end Gain Invariant Modeling for Wake Word Spotting
Since the WW model is trained with the AFE-processed audio data, its performance is sensitive to AFE variations, such as gain changes.
Adaptive Gradient Method with Resilience and Momentum
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control the parameter-wise learning rate (e. g., Adam and RMSProp).
Multi-Task Self-Supervised Pre-Training for Music Classification
Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain.
AutoSampling: Search for Effective Data Sampling Schedules
Data sampling acts as a pivotal role in training deep learning models.
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed.
Once Quantized for All: Progressively Searching for Quantized Compact Models
Automatic search of Quantized Neural Networks (QNN) has attracted a lot of attention.
Low-bit quantization and quantization-aware training for small-footprint keyword spotting
We investigate low-bit quantization to reduce computational cost of deep neural network (DNN) based keyword spotting (KWS).
Federated Self-Supervised Learning for Acoustic Event Classification
Standard acoustic event classification (AEC) solutions require large-scale collection of data from client devices for model optimization.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework
We conclude that this improvement in ASC performance comes from the regularization effect of using AET and not from the network's improved ability to discern between acoustic events.
Global Priors Guided Modulation Network for Joint Super-Resolution and Inverse Tone-Mapping
Joint super-resolution and inverse tone-mapping (SR-ITM) aims to enhance the visual quality of videos that have quality deficiencies in resolution and dynamic range.
SDRTV-to-HDRTV Conversion via Spatial-Temporal Feature Fusion
To evaluate the performance of the proposed method, we construct a corresponding multi-frame dataset using HDR video of the HDR10 standard to conduct a comprehensive evaluation of different methods.
LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting.
Handling the Alignment for Wake Word Detection: A Comparison Between Alignment-Based, Alignment-Free and Hybrid Approaches
The third, proposed by us, is a hybrid solution in which the model is trained with a small set of aligned data and then tuned with a sizeable unaligned dataset.
Quality-aware Pre-trained Models for Blind Image Quality Assessment
Blind image quality assessment (BIQA) aims to automatically evaluate the perceived quality of a single image, whose performance has been improved by deep learning-based methods in recent years.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment
\textit{Second}, the perceptual quality of a video exhibits a multi-distortion distribution, due to the differences in the duration and probability of occurrence for various distortions.
Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment
Video quality assessment (VQA) has attracted growing attention in recent years.
Blind Image Super-resolution with Rich Texture-Aware Codebooks
However, we find that a codebook based on HR reconstruction may not effectively capture the complex correlations between low-resolution (LR) and HR images.
FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation
Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted.
AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition
Wearable devices like smart glasses are approaching the compute capability to seamlessly generate real-time closed captions for live conversations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
KVQ: Kwai Video Quality Assessment for Short-form Videos
Short-form UGC video platforms, like Kwai and TikTok, have been an emerging and irreplaceable mainstream media form, thriving on user-friendly engagement, and kaleidoscope creation, etc.
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
Diffusion-based methods, endowed with a formidable generative prior, have received increasing attention in Image Super-Resolution (ISR) recently.
CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement
Specifically, the ITA module aggregates temporal information from consecutive frames and coding priors, while the MNA module globally captures spatial information guided by residual frames.
CasSR: Activating Image Power for Real-World Image Super-Resolution
In particular, we develop a cascaded controllable diffusion model that aims to optimize the extraction of information from low-resolution images.
Consistency Models Improve Diffusion Inverse Solvers
In addition, we propose a new family of DIS using pure CM.
NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results
This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained.
