Search Results for author:
Found 37 papers, 12 papers with code
Noise Learning for Text Classification: A Benchmark
However, we find that noise learning in text classification is relatively underdeveloped: 1. many methods that have been proven effective in the image domain are not explored in text classification, 2. it is difficult to conduct a fair comparison between previous studies as they do experiments in different noise settings.
Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method
Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels.
Anomaly Detection In Surveillance Videos
Multiple Instance Learning
+1
A Large-scale Interpretable Multi-modality Benchmark for Facial Image Forgery Localization
Leveraging the MMTT dataset, we develop ForgeryTalker, an architecture designed for concurrent forgery localization and interpretation.
Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search
To enable the training and evaluation of this new task, we construct a large-scale image-text Pedestrian Anomaly Behavior (PAB) benchmark, featuring a broad spectrum of actions, e. g., running, performing, playing soccer, and the corresponding anomalies, e. g., lying, being hit, and falling of the same identity.
DOGE: Towards Versatile Visual Document Grounding and Referring
In recent years, Multimodal Large Language Models (MLLMs) have increasingly emphasized grounding and referring capabilities to achieve detailed understanding and flexible user interaction.
Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples.
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition
In the first branch, a Domain Temporal Encoder is employed to capture temporal features for both the source and target domains.
ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
Existing clinical diagnostic evaluation benchmarks for evaluating medical agents powered by LLMs have severe limitations.
Graph Feedback Bandits with Similar Arms
When the means of arms are independently generated from some distribution, we provide regret upper bounds for both algorithms and discuss the sub-linearity of bounds in relation to the distribution of means.
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
A total of 196 participants have registered in the video track.
Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-$\mathrm{M^2}$DF)
In each view, we fuse the prompt embedding as consistent information with visual and the global or local temporal context to overcome the overlapping distribution of classes and outliers.
Forced Exploration in Bandit Problems
This paper aims to design a multi-armed bandit algorithm that can be implemented without using information about the reward distribution while still achieving substantial regret upper bounds.
Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CP$\mathbf{M^2}$C)
Although some multi-modal works use labels as supplementary to construct prototypes of support videos, they can not use this information for query videos.
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Finally, we systematically evaluate and analyze eight mainstream LLMs and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks.
Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition
The second module (MLT) focuses on the Multiple-level feature of the support prototype and query sample to mine more information for the alignment, which operates on different level features.
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text.
Ranked #1 on
Text based Person Retrieval
on ICFG-PEDES
(using extra training data)
Discounted Thompson Sampling for Non-Stationary Bandit Problems
Under mild assumptions, we show that DS-TS with Gaussian priors can achieve nearly optimal regret bound on the order of $\tilde{O}(\sqrt{TB_T})$ for abruptly changing and $\tilde{O}(T^{\beta})$ for smoothly changing, where $T$ is the number of time steps, $B_T$ is the number of breakpoints, $\beta$ is associated with the smoothly changing environment and $\tilde{O}$ hides the parameters independent of $T$ as well as logarithmic terms.
Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism
In response to this problem, we introduce the Coordinate Attention (CA) module to replace the Res Block to reduce the number of parameters, and cooperate with the spatial information extraction network above to strengthen the information extraction ability.
FSDNet-An efficient fire detection network for complex scenarios based on YOLOv3 and DenseNet
Fire is one of the common disasters in daily life.
YOLO-Drone:Airborne real-time detection of dense small objects from high-altitude perspective
With regards to UAVDT, the YOLO-Drone exhibits both high real-time inference speed of 53 FPS and a maximum mAP of 34. 04%.
Ranked #1 on
Object Detection
on India Driving Dataset
Landslide Susceptibility Prediction Modeling Based on Self-Screening Deep Learning Model
In conclusion, compared with some existing traditional machine learning, the SGCN-LSTM model proposed in this paper has higher landslide prediction accuracy and better robustness, and has a good application prospect in the LSP field.
ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization
In the subsequent stage, we apply pixel-level data augmentation techniques to generate corrupted normal images and their corresponding pixel labels.
Ranked #72 on
Anomaly Detection
on MVTec AD
(using extra training data)
Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond
In this paper, we introduce a novel Generative Adversarial Networks alike framework, referred to as GAN-MAE, where a generator is used to generate the masked patches according to the remaining visible patches, and a discriminator is employed to predict whether the patch is synthesized by the generator.
Uncertainty-Aware Image Captioning
It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it.
Progressive Text-to-Image Generation
Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space.
Progressive Glass Segmentation
First, we attempt to bridge the characteristic gap between different levels of features by developing a Discriminability Enhancement (DE) module which enables level-specific features to be a more discriminative representation, alleviating the features incompatibility for fusion.
Detecting Small Objects in Thermal Images Using Single-Shot Detector
In this paper, we proposed DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection.
Generating Superpixels for High-resolution Images with Decoupled Patch Calibration
Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning.
ReGO: Reference-Guided Outpainting for Scenery Image
We aim to tackle the challenging yet practical scenery image outpainting task in this work.
1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit
For the text spotting task, we detect the characters on integrated circuit and classify them based on yolov5 detection model.
AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation
Superpixel segmentation has seen significant progress benefiting from the deep convolutional networks.
DONet: Dual Objective Networks for Skin Lesion Segmentation
Skin lesion segmentation is a crucial step in the computer-aided diagnosis of dermoscopic images.
Sketch-Guided Scenery Image Outpainting
In this work, we take the image outpainting one step forward by allowing users to harvest personal custom outpainting results using sketches as the guidance.
IoU-uniform R-CNN: Breaking Through the Limitations of RPN
Region Proposal Network (RPN) is the cornerstone of two-stage object detectors, it generates a sparse set of object proposals and alleviates the extrem foregroundbackground class imbalance problem during training.
Localization-aware Channel Pruning for Object Detection
In this paper, based on discrimination-aware channel pruning (DCP) which is state-of-the-art pruning method for classification, we propose a localization-aware auxiliary network to find out the channels with key information for classification and regression so that we can conduct channel pruning directly for object detection, which saves lots of time and computing resources.
VrR-VG: Refocusing Visually-Relevant Relationships
Relationships encode the interactions among individual instances, and play a critical role in deep visual scene understanding.
Multi-view Point Cloud Registration with Adaptive Convergence Threshold and its Application on 3D Model Retrieval
In this paper, we propose a framework to reconstruct the 3D models by the multi-view point cloud registration algorithm with adaptive convergence threshold, and subsequently apply it to 3D model retrieval.
