Search Results for author:
Found 27 papers, 6 papers with code
EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
Owing to the combination of the unified architecture and pre-training task, EVE is easy to scale up, enabling better downstream performance with fewer resources and faster training speed.
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
We show that only language-paired two-modality data is sufficient to connect all modalities.
ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition
Specifically, with the introduction of three conceptual layers--Sampling Layer, Data Augmentation Layer, and Resilient Layer -- we develop three "boosters" -- R-Frame, Mix-up, and C-Drop -- to enrich the per-epoch training data by dense-sampling, synthesizing, and simulating, respectively.
FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model.
Algorithm Selection for Deep Active Learning with Imbalanced Datasets
Extensive experiments in multi-class and multi-label applications demonstrate TAILOR's effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms.
Simple Yet Surprisingly Effective Training Strategies for LSTMs in Sensor-Based Human Activity Recognition
What remains a major challenge though is the sporadic activity recognition (SAR) problem, where activities of interest tend to be non periodic, and occur less frequently when compared with the often large amount of irrelevant background activities.
MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning
Our method performs joint masking on image-text input and integrates both implicit and explicit targets for the masked signals to recover.
Efficient population coding of sensory stimuli
Here we derive a general theory of optimal population coding with neuronal activation functions of any shape, different types of noise and heterogeneous firing rates of the neurons by maximizing the Shannon mutual information between a stimulus and the neuronal spiking output subject to a constrain on the maximal firing rate.
A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy
Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio.
Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
In two typical cross-domain semantic segmentation tasks, i. e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy.
GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
First, we propose a novel label prediction method, Isolated Graph Learning (IGL).
SSDL: Self-Supervised Dictionary Learning
Inspired by the concept of self-supervised learning (e. g., setting the pretext task to generate a universal model for the downstream task), we propose a Self-Supervised Dictionary Learning (SSDL) framework to address this challenge.
MDFM: Multi-Decision Fusing Model for Few-Shot Learning
Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model.
MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
Apply the trained FEM to acquire the novel data's features and recognize them.
CIM: Class-Irrelevant Mapping for Few-Shot Classification
(2) Use the FEM to extract the features of novel data (with few labeled samples and totally different categories from base data), then classify them with the to-be-designed classifier.
SAHDL: Sparse Attention Hypergraph Regularized Dictionary Learning
In this paper, we propose a hypergraph based sparse attention mechanism to tackle this issue and embed it into dictionary learning.
DLDL: Dynamic Label Dictionary Learning via Hypergraph Regularization
To tackle this issue, we propose a Dynamic Label Dictionary Learning (DLDL) algorithm to generate the soft label matrix for unlabeled data.
A Dichotomy for Real Boolean Holant Problems
We prove a complexity dichotomy for Holant problems on the boolean domain with arbitrary sets of real-valued constraint functions.
Computational Complexity
Objects365: A Large-Scale, High-Quality Dataset for Object Detection
Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation.
Class specific or shared? A cascaded dictionary learning framework for image classification
Dictionary learning methods can be split into: i) class specific dictionary learning ii) class shared dictionary learning.
Shape Robust Text Detection with Progressive Scale Expansion Network
Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.
Ranked #12 on
Scene Text Detection
on SCUT-CTW1500
Label Embedded Dictionary Learning for Image Classification
Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Scene Text Detection with Supervised Pyramid Context Network
We propose a supervised pyramid context network (SPCNET) to precisely locate text regions while suppressing false positives.
Ranked #2 on
Scene Text Detection
on ICDAR 2013
CrowdHuman: A Benchmark for Detecting Human in a Crowd
There are a total of $470K$ human instances from the train and validation subsets, and $~22. 6$ persons per image, with various kinds of occlusions in the dataset.
Ranked #7 on
Pedestrian Detection
on Caltech
(using extra training data)
Repulsion Loss: Detecting Pedestrians in a Crowd
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
Ranked #9 on
Pedestrian Detection
on Caltech
(using extra training data)
Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks
This paper presents a method of integrating a mixture of object models and region-based convolutional networks for accurate object detection.
