Search Results for author:
Found 52 papers, 20 papers with code
Moment Quantization for Video Temporal Grounding
In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments.
Versatile Multimodal Controls for Expressive Talking Human Animation
AI-generated content faces similar requirements, where users not only need automatic generation of lip synchronization and basic gestures from audio input but also desire semantically accurate and expressive body movement that can be ``directly guided'' through text descriptions.
StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition
Most deep learning-based methods in an end-to-end manner cannot extract global features with sufficient semantic information from RGB images.
REGNav: Room Expert Guided Image-Goal Navigation
Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their similarity and predicts actions.
Referencing Where to Focus: Improving VisualGrounding with Referential Query
It consists of the query adaption module that can be seamlessly integrated into CLIP and generate the referential query to provide the prior context for decoder, along with a task-specific decoder.
PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation
In this paper, we propose a simple yet effective semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation, whose goal is to generate high-fidelity pseudo labels by learning robust and diverse features in the training process.
Semantic-aware Representation Learning for Homography Estimation
In our work, we seek another way to use the semantic information, that is semantic-aware feature representation learning framework. Based on this, we propose SRMatcher, a new detector-free feature matching method, which encourages the network to learn integrated semantic feature representation. Specifically, to capture precise and rich semantics, we leverage the capabilities of recently popularized vision foundation models (VFMs) trained on extensive datasets.
Towards Generalizable Multi-Object Tracking
Effective trackers should demonstrate a high degree of generalizability across diverse scenarios.
Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding
To tackle this limitation, we present a Region-Guided TRansformer (RGTR) for temporal sentence grounding, which diversifies moment queries to eliminate overlapped and redundant predictions.
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection
The success of knowledge distillation mainly relies on how to keep the feature discrepancy between the teacher and student model, in which it assumes that: (1) the teacher model can jointly represent two different distributions for the normal and abnormal patterns, while (2) the student model can only reconstruct the normal distribution.
Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data.
Robust Noisy Label Learning via Two-Stream Sample Distillation
Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning.
Camera-aware Label Refinement for Unsupervised Person Re-identification
Unsupervised person re-identification aims to retrieve images of a specified person without identity labels.
Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes
To this end, we first devise innovative strategies to adaptively select high-quality positive and negative classes from the label space, by modeling both the confidence and rank of a class in relation to those of the target class.
Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction
Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model.
Molecule Design by Latent Prompt Transformer
We propose the Latent Prompt Transformer (LPT), a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution modeled by a neural transformation of Gaussian white noise; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt.
Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking
In this paper, we propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets, so as to achieve robust data association in the tracking process.
FFINet: Future Feedback Interaction Network for Motion Forecasting
In this paper, we propose a novel Future Feedback Interaction Network (FFINet) to aggregate features the current observations and potential future interactions for trajectory prediction.
MLF-DET: Multi-Level Fusion for Cross-Modal 3D Object Detection
In this paper, we propose a novel and effective Multi-Level Fusion network, named as MLF-DET, for high-performance cross-modal 3D object DETection, which integrates both the feature-level fusion and decision-level fusion to fully utilize the information in the image.
Understanding the Overfitting of the Episodic Meta-training
Specifically, we select the teacher model as the one with the best validation accuracy during meta-training and restrict the symmetric Kullback-Leibler (SKL) divergence between the output distribution of the linear classifier of the teacher model and that of the student model.
T-former: An Efficient Transformer for Image Inpainting
And based on this attention, a network called $T$-former is designed for image inpainting.
Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection
Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection.
MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target.
Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization
To this end, we propose a unified framework, termed Noisy Pseudo-Label Learning, to handle both location biases and category errors.
Trajectory Unified Transformer for Pedestrian Trajectory Prediction
Pedestrian trajectory prediction is an essentially connecting link to understanding human behavior.
Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition
Learning discriminative features from very few labeled samples to identify novel classes has received increasing attention in skeleton-based action recognition.
Action Recognition
Few-Shot Skeleton-Based Action Recognition
+1
Sparse Instance Conditioned Multimodal Trajectory Prediction
Specifically, SICNet learns comprehensive sparse instances, i. e., representative points of the future trajectory, through a mask generated by a long short-term memory encoder and uses the memory mechanism to store and retrieve such sparse instances.
StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition
In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment.
Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e. g., context and background, in an untrimmed video.
Social Interpretable Tree for Pedestrian Trajectory Prediction
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications.
TransVPR: Transformer-based place recognition with multi-level attention aggregation
In addition, the output tokens from Transformer layers filtered by the fused attention mask are considered as key-patch descriptors, which are used to perform spatial matching to re-rank the candidates retrieved by the global image features.
Auxiliary Loss Reweighting for Image Inpainting
TPL and TSL are supersets of perceptual and style losses and release the auxiliary potential of standard perceptual and style losses.
Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction
Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area.
SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians.
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Meanwhile, we use a sparse directed temporal graph to model the motion tendency, thus to facilitate the prediction based on the observed direction.
Progressive Depth Learning for Single Image Dehazing
However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase.
Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-truth labels.
Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
The radical student uses multi-source supervision signals from the same task to update parameters, while the calm teacher uses a single-source supervision signal to update parameters.
End-to-End Multi-Object Tracking with Global Response Map
Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated.
Meta Corrupted Pixels Mining for Medical Image Segmentation
However the training of deep neural network requires a large amount of samples with high-quality annotations.
Multiple Object Tracking by Flowing and Fusing
Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID).
Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification
In this paper, we propose a simple yet effective feedforward attention network to address the two mentioned problems, in which a novel consistent attention regularizer and an improved triplet loss are designed to learn foreground attentive features for person Re-ID.
Frame-wise Motion and Appearance for Real-time Multiple Object Tracking
The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames.
Person-in-WiFi: Fine-grained Person Perception using WiFi
Fine-grained person perception such as body segmentation and pose estimation has been achieved with many 2D and 3D sensors such as RGB/depth cameras, radars (e. g., RF-Pose) and LiDARs.
SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection
In this paper, we propose a simple yet effective Siamese Edge-Enhancement Network (SE2Net) to preserve the edge structure for salient object detection.
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance.
Ranked #24 on
Image Classification
on Clothing1M
(using extra training data)
Discriminative Feature Learning with Foreground Attention for Person Re-Identification
Specifically, a novel foreground attentive subnetwork is designed to drive the network's attention, in which a decoder network is used to reconstruct the binary mask by using a novel local regression loss function, and an encoder network is regularized by the decoder network to focus its attention on the foreground persons.
Deep Self-Paced Learning for Person Re-Identification
In this paper, we propose a novel deep self-paced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to help the relative distance metric training the deep neural network, so as to learn the stable and discriminative features for person Re-ID.
Large Margin Learning in Set to Set Similarity Comparison for Person Re-identification
The class-identity term keeps the intra-class samples within each camera view gathering together, the relative distance term maximizes the distance between the intra-class class set and inter-class set across different camera views, and the regularization term smoothness the parameters of deep convolutional neural network (CNN).
Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
In this paper, we present a novel deep ranking model with feature learning and fusion by learning a large adaptive margin between the intra-class distance and inter-class distance to solve the person re-identification problem.
Point to Set Similarity Based Deep Feature Learning for Person Re-Identification
One of the key issues for deep learning based person Re-ID is the selection of proper similarity comparison criteria, and the performance of learned features using existing criterion based on pairwise similarity is still limited, because only P2P distances are mostly considered.
Person Re-Identification by Multi-Channel Parts-Based CNN With Improved Triplet Loss Function
Person re-identification across cameras remains a very challenging problem, especially when there are no overlapping fields of view between cameras.
