Search Results for author:
Found 48 papers, 24 papers with code
From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human annotations.
A Benchmark for Multi-Lingual Vision-Language Learning in Remote Sensing Image Captioning
Remote Sensing Image Captioning (RSIC) is a cross-modal field bridging vision and language, aimed at automatically generating natural language descriptions of features and scenes in remote sensing imagery.
FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation
The core of FGAseg is a Pixel-Level Alignment module that employs a cross-modal attention mechanism and a text-pixel alignment loss to refine the coarse-grained alignment from CLIP, achieving finer-grained pixel-text semantic alignment.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
SignEye: Traffic Sign Interpretation from Vehicle First-Person View
Meanwhile, we develop a traffic guidance assistant (TGA) scenario application to re-explore the role of traffic signs in ADS as a complement to popular autonomous technologies (such as obstacle perception).
Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural Scenes
In addition, to validate the scene robustness of the SM-Net, we conduct experiments on traffic, industrial, and natural scene datasets.
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
A straightforward pipeline for zero-shot out-of-distribution (OOD) detection involves selecting potential OOD labels from an extensive semantic pool and then leveraging a pre-trained vision-language model to perform classification on both in-distribution (ID) and OOD labels.
Revisiting Essential and Nonessential Settings of Evidential Deep Learning
Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant attention.
Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera
The irregular contour representation is one of the tough challenges in scene text detection.
Focus Entirety and Perceive Environment for Arbitrary-Shaped Text Detection
The latter extracts region-level information and encourages the model to focus on the distribution of positive samples in the vicinity of a pixel, which perceives environment information.
A Comprehensive Survey on Evidential Deep Learning and Its Applications
To address this challenge, a novel paradigm called Evidential Deep Learning (EDL) has emerged, providing reliable uncertainty estimation with minimal additional computation in a single forward pass.
Quantum-inspired Interpretable Deep Learning Architecture for Text Sentiment Analysis
Text has become the predominant form of communication on social media, embedding a wealth of emotional nuances.
A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
We propose OneShotLP, a training-free framework for video-based license plate detection and recognition, leveraging these advanced models.
Text-only Synthesis for Image Captioning
In this paper, we propose Text-only Synthesis for Image Captioning (ToCa), which further advances this relaxation with fewer human labor and less computing time.
U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation
To address this issue, we leverage the inherent capabilities of the model itself to discover the optimal equilibrium in multimodal fusion and introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation.
Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
Few-shot segmentation (FSS) for remote sensing (RS) imagery leverages supporting information from limited annotated samples to achieve query segmentation of novel classes.
Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Text
Few-shot learning aims to generalize the recognizer from seen categories to an entirely novel scenario.
Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation
Then, based on the theory, we design a DPD algorithm which is composed by a training paradigm and proxy domain generator to enhance the domain generalization of the confidence-threshold learner.
NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images
Considering the absence of a dataset for this task, a large-scale Dataset (NWPU-MOC) is collected, consisting of 3, 416 scenes with a resolution of 1024 $\times$ 1024 pixels, and well-annotated using 14 fine-grained object categories.
SamLP: A Customized Segment Anything Model for License Plate Detection
Meanwhile, the proposed SamLP has great few-shot and zero-shot learning ability, which shows the potential of transferring vision foundation model.
Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation
Such agents are typically required to execute user instructions in an online manner, leading us to explore the use of unlabeled test samples for effective online model adaptation.
Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding
In this manner, our framework is able to learn the unified representations of uni-modal or multi-modal skeleton input, which is flexible to different kinds of modality input for robust action understanding in practical cases.
Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation
Despite the great progress of unsupervised domain adaptation (UDA) with the deep neural networks, current UDA models are opaque and cannot provide promising explanations, limiting their applications in the scenarios that require safe and controllable model decisions.
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
Theoretically, we show the convergence guarantee of the dual regulators.
Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing
In this paper, to balance the feature learning processes of different modalities, a dynamic gradient modulation (DGM) mechanism is explored, where a novel and effective metric function is designed to measure the imbalanced feature learning between audio and visual modalities.
Imbalanced Aircraft Data Anomaly Detection
Anomaly detection in temporal data from sensors under aviation scenarios is a practical but challenging task: 1) long temporal data is difficult to extract contextual information with temporal correlation; 2) the anomalous data are rare in time series, causing normal/abnormal imbalance in anomaly detection, making the detector classification degenerate or even fail.
Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception
We argue that, for an event residing in one modality, the modality itself should provide ample presence evidence of this event, while the other complementary modality is encouraged to afford the absence evidence as a reference signal.
Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization
Targeting at recognizing and localizing action instances with only video-level labels during training, Weakly-supervised Temporal Action Localization (WTAL) has achieved significant progress in recent years.
Open Set Learning
Weakly-supervised Temporal Action Localization
+1
Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
Here we propose a scale-sensitive generalized loss to tackle this problem.
Ranked #10 on
Object Counting
on FSC147
Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects
The mainstream crowd counting methods regress density map and integrate it to obtain counting results.
MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting
RGB-Thermal (RGB-T) crowd counting is a challenging task, which uses thermal images as complementary information to RGB images to deal with the decreased performance of unimodal RGB-based methods in scenes with low-illumination or similar backgrounds.
Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher
The core reason of intrinsic scale shift being one of the most essential issues in crowd localization is that it is ubiquitous in crowd scenes and makes scale distribution chaotic.
Learning Muti-expert Distribution Calibration for Long-tailed Video Classification
Most existing state-of-the-art video classification methods assume that the training data obey a uniform distribution.
Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding
Then, a commonsense-aware interaction module is designed to obtain bridged visual and text features by utilizing the learned commonsense concepts.
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training.
DR.VIC: Decomposition and Reasoning for Video Individual Counting
Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians with separate identities in each following frame.
Weakly-Supervised Video Object Grounding via Causal Intervention
With this in mind, we design a unified causal framework to learn the deconfounded object-relevant association for more accurate and robust video object grounding.
Audio-visual Representation Learning for Anomaly Events Detection in Crowds
The second is an audio CNN for encoding Log Mel-Spectrogram of audio signals.
LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map.
Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
In addition, due to domain gaps between different datasets, the performance is dramatically decreased when re-ID models pre-trained on label-rich datasets (source domain) are directly applied to other unlabeled datasets (target domain).
Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer
To this end, we propose a Dilated Convolutional Swin Transformer (DCST) for congested crowd scenes.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark
Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos.
Health Status Prediction with Local-Global Heterogeneous Behavior Graph
However, these data streams are multi-source and heterogeneous, containing complex temporal structures with local contextual and global temporal aspects, which makes the feature learning and data joint utilization challenging.
Fast Video Moment Retrieval
To tackle this issue, we replace the cross-modal interaction module with a cross-modal common space, in which moment-query alignment is learned and efficient moment search can be performed.
Active Universal Domain Adaptation
This paper proposes a new paradigm for unsupervised domain adaptation, termed as Active Universal Domain Adaptation (AUDA), which removes all label set assumptions and aims for not only recognizing target samples from source classes but also inferring those from target-private classes by using active learning to annotate a small budget of target data.
Learning Independent Instance Maps for Crowd Localization
Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps.
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating.
I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs
To effectively leverage the knowledge graph, we design a novel Two-Stream Graph Convolutional Network (TS-GCN) consisting of a classifier branch and an instance branch.
Ranked #5 on
Zero-Shot Action Recognition
on Olympics
