Search Results for author:
Found 24 papers, 11 papers with code
Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression
Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving.
SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition
With the help of flexible prompting and gated alignments, SSPA is generalizable to specific domains.
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection
Vision-based roadside 3D object detection has attracted rising attention in autonomous driving domain, since it encompasses inherent advantages in reducing blind spots and expanding perception range.
Training-Free Unsupervised Prompt for Vision-Language Models
In light of this, we propose Training-Free Unsupervised Prompts (TFUP), which maximally preserves the inherent representation capabilities and enhances them with a residual connection to similarity-based prediction probabilities in a training-free and labeling-free manner.
PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition
In contrast to the unidirectional fusion in previous works, we introduce a Dual-Modal Attention (DMA) that enables bidirectional interaction between textual and visual features, yielding context-aware label representations and semantic-related visual representations, which are subsequently used to calculate similarities and generate final predictions for all labels.
CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing
Second to enhance motion coherence and extend the generalization of appearance content to creative textual prompts we propose the causal motion-enhanced attention mechanism.
Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection
In this paper, we study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods, e. g., GANs and diffusion models.
ProtoHPE: Prototype-guided High-frequency Patch Enhancement for Visible-Infrared Person Re-identification
In contrast, we find that some cross-modal correlated high-frequency components contain discriminative visual patterns and are less affected by variations such as wavelength, pose, and background clutter than holistic images.
Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation
Moreover, to address the semantic conflicts between image and frequency domains, the forgery-aware mutual module is developed to further enable the effective interaction of disparate image and frequency features, resulting in aligned and comprehensive visual forgery representations.
Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation
State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e. g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR.
General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone
Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation.
NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition
To achieve the collaborative learning in long-tailed learning, the balanced online distillation is proposed to force the consistent predictions among different experts and augmented copies, which reduces the learning uncertainties.
Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes
Modern autonomous driving systems are typically divided into three main tasks: perception, prediction, and planning.
Ranked #1 on
Trajectory Planning
on nuScenes
FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing
The availability of handy multi-modal (i. e., RGB-D) sensors has brought about a surge of face anti-spoofing research.
Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
A contrastive loss is employed to align such augmented text and image representations on downstream tasks.
Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition
The proposed APP is employed to select the most informative patches on CNN features, and ATP discards unimportant tokens in ViT.
Ranked #10 on
Facial Expression Recognition (FER)
on RAF-DB
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Nested Collaborative Learning for Long-Tailed Visual Recognition
NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively.
Ranked #7 on
Long-tail Learning
on CIFAR-10-LT (ρ=50)
Coarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognition
To be specific, the universal features denote the general characteristic of facial emotions within a period and the unique features denote the specific characteristic at this moment.
Facial Expression Recognition
Facial Expression Recognition (FER)
Defending Black-box Skeleton-based Human Activity Classifiers
Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary sampling scheme based on natural motion manifolds, and (3) a new post-train Bayesian strategy for black-box defense.
LAE : Long-tailed Age Estimation
To improve the performance of facial age estimation, we first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on.
Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection
To bridge the gap to real-world applications, we introduce a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask).
Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review
Although ethnic bias has been verified to severely affect the performance of face recognition systems, it still remains an open research problem in face anti-spoofing.
CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing
Ethnic bias has proven to negatively affect the performance of face recognition systems, and it remains an open research problem in face anti-spoofing.
Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing
Regardless of the usage of deep learning and handcrafted methods, the dynamic information from videos and the effect of cross-ethnicity are rarely considered in face anti-spoofing.
