Search Results for author:
Found 33 papers, 21 papers with code
Relation-Rich Visual Document Generator for Visual Information Extraction
Despite advances in Large Language Models (LLMs) and Multimodal LLMs (MLLMs) for visual document understanding (VDU), visual information extraction (VIE) from relation-rich documents remains challenging due to the layout diversity and limited training data.
Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model
Open-vocabulary panoptic segmentation remains a challenging problem.
Open Vocabulary Panoptic Segmentation
Panoptic Segmentation
+1
ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning
We achieve the superior performance on 17 diverse natural language tasks including natural language understanding (NLU) and question answering (QA) tasks by tuning only 0. 3% of parameters of the PLMs.
Natural Language Understanding
parameter-efficient fine-tuning
+2
The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks that compromise safety and reliability.
SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation
We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks.
Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
Semi-supervised learning (SSL) has achieved remarkable performance with a small fraction of labeled data by leveraging vast amounts of unlabeled data from the Internet.
RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Images
In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image.
LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models
The performance of speaker verification (SV) models may drop dramatically in noisy environments.
D4AM: A General Denoising Framework for Downstream Acoustic Models
To our knowledge, this is the first work that deploys an effective combination scheme of regression (denoising) and classification (ASR) objectives to derive a general pre-processor applicable to various unseen ASR systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Domain-Generalized Face Anti-Spoofing with Unknown Attacks
Although face anti-spoofing (FAS) methods have achieved remarkable performance on specific domains or attack types, few studies have focused on the simultaneous presence of domain changes and unknown attacks, which is closer to real application scenarios.
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision
To our knowledge, this is the first work on weakly-supervised continual learning for instance segmentation of images.
Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training
It can improve the robustness of learning-based methods with flow-guided keyframes and well-established depth prior.
NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling
NASTAR uses a feedback mechanism to simulate adaptive training data via a noise extractor and a retrieval model.
Continual Learning for Visual Search with Backward Consistent Feature Embedding
In visual search, the gallery set could be incrementally growing and added to the database in practice.
STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing
The STR mechanism treats the spatial transformation as the message passing process, and the relation between the view poses and the routing weights is modeled by an end-to-end trainable neural network.
Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multi-view.
Ranked #6 on
3D Multi-Person Pose Estimation
on Campus
3D Video Stabilization With Depth Estimation by CNN-Based Optimization
We take advantage of the recent self-supervised framework on jointly learning depth and camera ego-motion estimation on raw videos.
Video-based Person Re-identification without Bells and Whistles
Besides, we discover the errors not only for the identity labels of tracklets but also for the evaluation protocol for the test data of MARS.
EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING
Although CondConv is effective for the performance enhancement of a deep model, it is currently applied to individual tasks only.
Ranked #1 on
Continual Learning
on Flowers (Fine-grained 6 Tasks)
360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales
Technically, the gaze information can be inferred from two different magnification levels: face orientation and eye orientation.
IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector
It is hard to detect on-road objects under various lighting conditions.
Compacting, Picking and Growing for Unforgetting Continual Learning
First, it can avoid forgetting (i. e., learn new tasks while remembering all previous tasks).
Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning
Simultaneously running multiple modules is a key requirement for a smart multimedia system for facial applications including face recognition, facial expression understanding, and gender identification.
Ranked #1 on
Gender Prediction
on FotW Gender
(using extra training data)
Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition
This paper aims at recognizing partially observed human actions in videos.
Data-specific Adaptive Threshold for Face Recognition and Authentication
Many face recognition systems boost the performance using deep learning models, but only a few researches go into the mechanisms for dealing with online registration.
Ranked #1 on
Face Recognition
on LFW (Online Open Set)
(using extra training data)
Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications
Automatic age and gender classification based on unconstrained images has become essential techniques on mobile devices.
Ranked #9 on
Age And Gender Classification
on Adience Gender
Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
We propose a novel method to merge convolutional neural-nets for the inference stage.
Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
In this paper, we present an object detection method that tackles the stingray detection problem based on aerial images.
Aesthetic Critiques Generation for Photos
Although aesthetic quality assessment has generated a great deal of interest in the last decade, most studies focus on providing a quality rating of good or bad for an image.
Learning Compact Binary Descriptors With Unsupervised Deep Neural Networks
In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching.
Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
SSDH is simple and can be realized by a slight enhancement of an existing deep architecture for classification; yet it is effective and outperforms other hashing approaches on several benchmarks and large datasets.
To Know Where We Are: Vision-Based Positioning in Outdoor Environments
Augmented reality (AR) displays become more and more popular recently, because of its high intuitiveness for humans and high-quality head-mounted display have rapidly developed.
Bayesian Fisher's Discriminant for Functional Data
We propose a Bayesian framework of Gaussian process in order to extend Fisher's discriminant to classify functional data such as spectra and images.
