Search Results for author:
Found 111 papers, 34 papers with code
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
The outputs from the teacher network are used as soft labels for supervising the training of a new network.
Ranked #25 on
Knowledge Distillation
on ImageNet
3D Hand Shape and Pose Estimation from a Single RGB Image
This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image.
Track to Detect and Segment: An Online Multi-Object Tracker
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking.
Ranked #1 on
Instance Segmentation
on nuScenes
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed.
Ranked #1 on
Hand Pose Estimation
on K2HPD
NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions
The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals.
GRiT: A Generative Region-to-text Transformer for Object Understanding
Specifically, GRiT consists of a visual encoder to extract image features, a foreground object extractor to localize objects, and a text decoder to generate open-set object descriptions.
Ranked #2 on
Dense Captioning
on Visual Genome
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
Recent transformer-based solutions have been introduced to estimate 3D human pose from 2D keypoint sequence by considering body joints among all frames globally to learn spatio-temporal correlation.
Ranked #6 on
Monocular 3D Human Pose Estimation
on Human3.6M
Model-based 3D Hand Reconstruction via Self-Supervised Learning
For the first time, we demonstrate the feasibility of training an accurate 3D hand reconstruction network without relying on manual annotations.
AiATrack: Attention in Attention for Transformer Visual Tracking
However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights, which inhibits further performance improvement.
Ranked #2 on
Visual Object Tracking
on NeedForSpeed
Kernel Cross-Correlator
Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking.
Non-iterative SLAM for Warehouse Robots Using Ground Textures
We present a novel visual SLAM method for the warehouse robot with a single downward-facing camera using ground textures.
Robotics
PointCloud Saliency Maps
Our motivation for constructing a saliency map is by point dropping, which is a non-differentiable operator.
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly.
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
In the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.
Ranked #5 on
Few-Shot Object Detection
on LVIS v1.0 val
Hand PointNet: 3D Hand Pose Estimation Using Point Sets
Convolutional Neural Network (CNN) has shown promising results for 3D hand pose estimation in depth images.
Ranked #7 on
Hand Pose Estimation
on HANDS 2017
SPAGAN: Shortest Path Graph Attention Network
SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods.
Kervolutional Neural Networks
Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks.
Structure-Aware Human-Action Generation
Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence.
Ranked #2 on
Human action generation
on NTU RGB+D 2D
Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene
Based on it, we formulate a hierarchical learning problem for 3D point cloud segmentation and propose a measurement evaluating consistency across various hierarchies.
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection
We consider the problem of Human-Object Interaction (HOI) Detection, which aims to locate and recognize HOI instances in the form of <human, action, object> in images.
Language-guided Human Motion Synthesis with Atomic Actions
In this paper, we propose ATOM (ATomic mOtion Modeling) to mitigate this problem, by decomposing actions into atomic actions, and employing a curriculum learning strategy to learn atomic action composition.
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
In this paper, we focus on skeleton-based action generation and propose to model smooth and diverse transitions on a latent space of action sequences with much lower dimensionality.
Ranked #4 on
Human action generation
on NTU RGB+D 2D
Learning Transferable Human-Object Interaction Detector With Natural Language Supervision
More specifically, we propose a new HOI visual encoder to detect the interacting humans and objects, and map them to a joint feature space to perform interaction recognition.
Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
To tackle the source data-absent problem, we present a novel two-stage source-free domain adaptation (SFDA) framework for medical image segmentation, where only a well-trained source segmentation model and unlabeled target data are available during domain adaptation.
Motion-driven Visual Tempo Learning for Video-based Action Recognition
Action visual tempo characterizes the dynamics and the temporal scale of an action, which is helpful to distinguish human actions that share high similarities in visual dynamics and appearance.
Ranked #14 on
Action Recognition
on Something-Something V1
Harnessing Low-Frequency Neural Fields for Few-Shot View Synthesis
We further propose a simple-yet-effective strategy for tuning the frequency to avoid overfitting few-shot inputs: enforcing consistency among the frequency domain of rendered 2D images.
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting
In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view.
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding.
Referring Video Object Segmentation
Semantic Segmentation
+2
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition
Moreover, by identifying key skeleton joints and temporal stages for each action class, our ST-NBNN can capture the essential spatio-temporal patterns that play key roles of recognizing actions, which is not always achievable by using end-to-end models.
High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition
To capture high-frequency personalized details, we transform the 3D mesh into the frequency domain, and propose a novel frequency decomposition loss to supervise each frequency component.
Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Field
A DecomposeNet learns to map each ray to its SVBRDF components: albedo, normal, and roughness.
Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temporal sampling points around a reference point.
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack
Adversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models.
Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNs
Articulated hand pose estimation plays an important role in human-computer interaction.
Actor-Action Semantic Segmentation with Region Masks
One major challenge for this task is that when an actor performs an action, different body parts of the actor provide different types of cues for the action category and may receive inconsistent action labeling when they are labeled independently.
Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics.
Max-Margin Structured Output Regression for Spatio-Temporal Action Localization
The mapping between a video and a spatio-temporal action trajectory is learned.
Multi-View Harmonized Bilinear Network for 3D Object Recognition
View-based methods have achieved considerable success in $3$D object recognition tasks.
Recognizing Human Actions as the Evolution of Pose Estimation Maps
Specifically, the evolution of pose estimation maps can be decomposed as an evolution of heatmaps, e. g., probabilistic maps, and an evolution of estimated 2D human poses, which denote the changes of body shape and body pose, respectively.
Ranked #1 on
Multimodal Activity Recognition
on UTD-MHAD
Conditional Generative Adversarial Network for Structured Domain Adaptation
In recent years, deep neural nets have triumphed over many computer vision problems, including semantic segmentation, which is a critical task in emerging autonomous driving and medical image diagnostics applications.
Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display
Multi-layer light field displays are a type of computational three-dimensional (3D) display which has recently gained increasing interest for its holographic-like effect and natural compatibility with 2D displays.
Bi-box Regression for Pedestrian Detection and Occlusion Estimation
The full body estimation branch is trained to regress full body regions for positive pedestrian proposals, while the visible part estimation branch is trained to regress visible part regions for both positive and negative pedestrian proposals.
Product Quantization Network for Fast Image Retrieval
Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features.
Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition
This deformable convolution can better utilize contextual joints for action and gesture recognition and is more robust to noisy joints.
Point-to-Point Regression PointNet for 3D Hand Pose Estimation
Convolutional Neural Networks (CNNs)-based methods for 3D hand pose estimation with depth cameras usually take 2D depth images as input and directly regress holistic 3D hand pose.
Weakly-supervised 3D Hand Pose Estimation from Monocular RGB Images
Compared with depth-based 3D hand pose estimation, it is more challenging to infer 3D hand pose from monocular RGB images, due to substantial depth ambiguity and the difficulty of obtaining fully-annotated training data.
Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior
We show that such data driven co-occurrence information from bottom-up can conveniently be incorporated in LDA with a Gaussian Markov prior, which combines top down probabilistic topic modeling with bottom up priors in a unified model.
Multi-feature Spectral Clustering with Minimax Optimization
To find a consensus clustering result that is agreeable to all feature modalities, our objective is to find a universal feature embedding, which not only fits each individual feature modality well, but also unifies different feature modalities by minimizing their pairwise disagreements.
Fast Action Proposals for Human Action Detection and Search
Assuming each action is performed by a human with meaningful motion, both appearance and motion cues are utilized to measure the actionness of the video tubes.
From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection
This representative selection problem is formulated as a sparse dictionary selection problem, i. e., choosing a few representatives object proposals to reconstruct the whole proposal pool.
3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images
We propose a simple, yet effective approach for real-time hand pose estimation from single depth images using three-dimensional Convolutional Neural Networks (3D CNNs).
HOPE: Hierarchical Object Prototype Encoding for Efficient Object Instance Search in Videos
This paper tackles the problem of efficient and effective object instance search in videos.
Fried Binary Embedding for High-Dimensional Visual Features
We argue that long binary codes (b O(d)) are critical to fully utilize the discriminative power of high-dimensional visual features, and can achieve better results in various tasks such as approximate nearest neighbour search.
Object Co-Skeletonization With Co-Segmentation
Recent advances in the joint processing of images have certainly shown its advantages over the individual processing.
Adaptive Exponential Smoothing for Online Filtering of Pixel Prediction Maps
We propose an efficient online video filtering method, called adaptive exponential filtering (AES) to refine pixel prediction maps.
Compressive Quantization for Fast Object Instance Search in Videos
Most of current visual search systems focus on image-to-image (point-to-point) search such as image and object retrieval.
Common Action Discovery and Localization in Unconstrained Videos
Similar to common object discovery in images or videos, it is of great interests to discover and locate common actions in videos, which can benefit many video analytics applications such as video summarization, search, and understanding.
Multi-Label Learning of Part Detectors for Heavily Occluded Pedestrian Detection
Detecting pedestrians that are partially occluded remains a challenging problem due to variations and uncertainties of partial occlusion patterns.
Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices
Effective and real-time eyeblink detection is of wide-range applications, such as deception detection, drive fatigue detection, face anti-spoofing, etc.
Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
Previous spatial-temporal action localization methods commonly follow the pipeline of object detection to estimate bounding boxes and labels of actions.
Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains.
Context-Integrated and Feature-Refined Network for Lightweight Object Parsing
The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM).
Temporal Pulses Driven Spiking Neural Network for Fast Object Recognition in Autonomous Driving
Accurate real-time object recognition from sensory data has long been a crucial and challenging task for autonomous driving.
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
Image Co-skeletonization via Co-segmentation
Object skeletonization in a single natural image is a challenging problem because there is hardly any prior knowledge about the object.
Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition
We first formulate generation of adversarial skeleton actions as a constrained optimization problem by representing or approximating the physiological and physical constraints with mathematical formulations.
Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion
In this work, we propose to consider hand and object jointly in feature space and explore the reciprocity of the two branches.
Temporal Distinct Representation Learning for Action Recognition
Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos.
Deep Reinforcement Learning with Label Embedding Reward for Supervised Image Hashing
Deep hashing has shown promising results in image retrieval and recognition.
Revisiting Modified Greedy Algorithm for Monotone Submodular Maximization with a Knapsack Constraint
Second, we enhance the modified greedy algorithm to derive a data-dependent upper bound on the optimum.
Learning Progressive Joint Propagation for Human Motion Prediction
Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.
Clustering Driven Deep Autoencoder for Video Anomaly Detection
Because of the ambiguous definition of anomaly and the complexity of real data, anomaly detection in videos is one of the most challenging problems in intelligent video surveillance.
Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation
To address this issue, we connect this structured output learning problem with the structured modeling framework in sequence transduction field.
Attention-Aware Noisy Label Learning for Image Classification
In this paper, the attention-aware noisy label learning approach ($A^2NL$) is proposed to improve the discriminative capability of the network trained on datasets with potential label noise.
Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective
In this paper, we investigate the bias-variance tradeoff brought by distillation with soft labels.
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision.
Ranked #12 on
Weakly Supervised Action Localization
on THUMOS14
Vocal Bursts Valence Prediction
Weakly Supervised Action Localization
+2
Interventional Domain Adaptation
To address this issue, we intervene in the learning of feature discriminability using unlabeled target data to guide it to get rid of the domain-specific part and be safely transferable.
Generation For Adaption: A GAN-Based Approach for 3D Domain Adaption with Point Cloud Data
Recent deep networks have achieved good performance on a variety of 3d points classification tasks.
ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization.
Ranked #7 on
Weakly Supervised Action Localization
on THUMOS’14
Video Polyp Segmentation
Weakly Supervised Action Localization
+2
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context
To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context.
Action Recognition
Weakly-supervised Temporal Action Localization
+1
NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field
In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes.
Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track
The base model training encourages the model to predict reliable predictions based on single modality (i. e., RGB or optical flow), based on the fusion of which a pseudo ground truth is generated and in turn used as supervision to train the base models.
OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
We introduce the task of open-vocabulary visual instance search (OVIS).
High Quality Disparity Remapping With Two-Stage Warping
In the second stage, we derive another warping model to refine warping results in less important regions by eliminating serious distortions in shape, disparity and 3D structure.
Vocal Bursts Intensity Prediction
Vocal Bursts Valence Prediction
Discovering Human Interactions With Large-Vocabulary Objects via Query and Multi-Scale Detection
In this work, we study the problem of human-object interaction (HOI) detection with large vocabulary object categories.
Stacked Homography Transformations for Multi-View Pedestrian Detection
This task is confronted with two challenges: how to establish the 3D correspondences from views to the BEV map and how to assemble occupancy information across views.
Ranked #7 on
Multiview Detection
on MultiviewX
A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder
Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series.
Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network
Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress.
Consistent 3D Hand Reconstruction in Video via self-supervised Learning
We present a method for reconstructing accurate and consistent 3D hands from a monocular video.
Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition
In recent years, graph convolutional networks (GCNs) play an increasingly critical role in skeleton-based human action recognition.
Efficient Video Instance Segmentation via Tracklet Query and Proposal
In addition, VisTR is not fully end-to-end learnable in multiple video clips as it requires a hand-crafted data association to link instance tracklets between successive clips.
Optical Flow for Video Super-Resolution: A Survey
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications.
Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w. r. t model's generalizability, performance, and training/inference memory footprint.
Neural Correspondence Field for Object Pose Estimation
Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the proposed method predicts 3D object coordinates at 3D query points sampled in the camera frustum.
PREF: Predictability Regularized Neural Motion Fields
We propose to regularize the estimated motion to be predictable.
Federated Learning with Privacy-Preserving Ensemble Attention Distillation
We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work.
NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest.
Progressive Multi-view Human Mesh Recovery with Self-Supervision
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e. g., motion capture, sport analysis) and robustness to single-view ambiguities.
Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction
Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules.
Neural Voting Field for Camera-Space 3D Hand Pose Estimation
We present a unified framework for camera-space 3D hand pose estimation from a single RGB image based on 3D implicit representation.
Ranked #4 on
3D Hand Pose Estimation
on HO-3D
3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data
Accurate facial landmark detection on wild images plays an essential role in human-computer interaction, entertainment, and medical applications.
RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture
The proposed framework consists of two significant components: Geometry Guided Diffusion and Mesh Optimization.
SOAR: Scene-debiasing Open-set Action Recognition
Deep models have the risk of utilizing spurious clues to make predictions, e. g., recognizing actions via classifying the background scene.
Open Set Video HOI detection from Action-Centric Chain-of-Look Prompting
To this end, we propose ACoLP, a model of Action-centric Chain-of-Look Prompting for open set video HOI detection.
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
To improve the generalization ability, we propose weakly-supervised self-consistency learning (WSCL) to leverage the weakly annotated images.
Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models
In this work, we propose that by incorporating correspondence regularization into diffusion models, the process of 3D editing can be significantly accelerated.
Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation
Evaluating speaker emotion in conversations is crucial for various applications requiring human-computer interaction.
Ranked #1 on
Multimodal Sentiment Analysis
on CMU-MOSEI
AMuSE: Adaptive Multimodal Analysis for Speaker Emotion Recognition in Group Conversations
This difficulty is compounded in group settings, where the emotion and its temporal evolution are not only influenced by the individual but also by external contexts like audience reaction and context of the ongoing conversation.
Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation
Then, we calculate the Area Under the Curve (AUC) difference between the two spectrums, so that each frequency band that captures either the overall or detailed shape is equitably considered.
FSC: Few-point Shape Completion
While previous studies have demonstrated successful 3D object shape completion with a sufficient number of points, they often fail in scenarios when a few points, e. g. tens of points, are observed.
