Search Results for author:
Found 71 papers, 29 papers with code
DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction
To tackle this problem, we propose a Divide-and-conquer 2D-3D cross-modal Alignment and Correction framework (DAC), which comprises Multimodal Dynamic Division (MDD) and Adaptive Alignment and Correction (AAC).
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity.
Ranked #5 on
Novel View Synthesis
on Tanks and Temples
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis
Our framework comprises two core modules: collaborative step mining and frame-to-step alignment.
Density Matters: Improved Core-set for Active Domain Adaptive Segmentation
Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation.
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
Bases have become an integral part of modern deep learning-based models for time series forecasting due to their ability to act as feature extractors or future references.
Ranked #47 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Few-shot Action Recognition via Intra- and Inter-Video Information Maximization
The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity.
Spatio-Temporal Point Process for Multiple Object Tracking
As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories.
Low-Rank Winograd Transformation for 3D Convolutional Neural Networks
This paper focuses on Winograd transformation in 3D convolutional neural networks (CNNs) that are more over-parameterized compared with the 2D version.
The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge
We present our 1st place solution to the Group Dance Multiple People Tracking Challenge.
Multi-Object Tracking
Multiple Object Tracking with Transformer
+1
Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition
In this paper, we propose a novel video frame sampler for few-shot action recognition to address this issue, where task-specific spatial-temporal frame sampling is achieved via a temporal selector (TS) and a spatial amplifier (SA).
FRIH: Fine-grained Region-aware Image Harmonization
Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image.
Controllable Augmentations for Video Representation Learning
The major reason is that the positive pairs, i. e., different clips sampled from the same video, have limited temporal receptive field, and usually share similar background but differ in motions.
End-to-end video instance segmentation via spatial-temporal graph neural networks
Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking.
Visual Sound Localization in the Wild by Cross-Modal Interference Erasing
Specifically, we observe that the previous practice of learning only a single audio representation is insufficient due to the additive nature of audio signals.
Uni-EDEN: Universal Encoder-Decoder Network by Multi-Granular Vision-Language Pre-training
Vision-language pre-training has been an emerging and fast-developing research topic, which transfers multi-modal knowledge from rich-resource pre-training task to limited-resource downstream tasks.
Speed Up Object Detection on Gigapixel-Level Images With Patch Arrangement
With the appearance of super high-resolution (e. g., gigapixel-level) images, performing efficient object detection on such images becomes an important issue.
Class-aware Sounding Objects Localization via Audiovisual Correspondence
To address this problem, we propose a two-stage step-by-step learning framework to localize and recognize sounding objects in complex audiovisual scenarios using only the correspondence between audio and vision.
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective
We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work.
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
We demonstrate that both temporal grains are beneficial to atomic action recognition.
Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting
Accurate prediction of the future given the past based on time series data is of paramount importance, since it opens the door for decision making and risk management ahead of time.
Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization
The crux of self-supervised video representation learning is to build general features from unlabeled videos.
TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e. g. background).
SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking
In addition, we add a localization branch to predict the localization accuracy, so that it can work as the replacement of the regression assistance link during inference.
Variational Pedestrian Detection
Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods.
Multi-Level Curriculum for Training a Distortion-Aware Barrel Distortion Rectification Model
In this paper, inspired by the curriculum learning, we analyze the barrel distortion rectification task in a progressive and meaningful manner.
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
In this paper, we address several inadequacies of current video object segmentation pipelines.
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes.
Finding Action Tubes with a Sparse-to-Dense Framework
The task of spatial-temporal action detection has attracted increasing attention among researchers.
Ranked #3 on
Action Detection
on UCF Sports
(Video-mAP 0.2 metric)
CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization.
AP-Loss for Accurate One-Stage Object Detection
This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem.
PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments
The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds.
Multiple Sound Sources Localization from Coarse to Fine
How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations.
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events.
TRP: Trained Rank Pruning for Efficient Deep Neural Networks
The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition.
Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
In this paper, we propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) that leverages dynamical directed spatial dependencies and long-range temporal dependencies to improve the accuracy of long-term traffic forecasting.
Trained Rank Pruning for Efficient Deep Neural Networks
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations.
Dual-stream shallow networks for facial micro-expression recognition
Micro-expressions are spontaneous, brief and subtle facial muscle movements that exposes underlying emotions.
ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
This paper tries to fill the gap by introducing a novel large-scale dataset, the Amur Tiger Re-identification in the Wild (ATRW) dataset.
Group Re-Identification with Multi-grained Matching and Integration
The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem. Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership.
Towards Accurate One-Stage Object Detection with AP-Loss
For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.
DNQ: Dynamic Network Quantization
Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices.
Trained Rank Pruning for Efficient Deep Neural Networks
We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training.
Network Decoupling: From Regular to Depthwise Separable Convolutions
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available.
Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages.
Enriched Long-term Recurrent Convolutional Network for Facial Micro-Expression Recognition
Facial micro-expression (ME) recognition has posed a huge challenge to researchers for its subtlety in motion and limited databases.
Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Network
In this paper, we propose a partition-masked Convolution Neural Network (CNN) to achieve compressed-video enhancement for the state-of-the-art coding standard, High Efficiency Video Coding (HECV).
Multimedia
Deep Neural Network Compression with Single and Multiple Level Quantization
In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary). We are the first to consider the network quantization from both width and depth level.
Unsupervised Deep Domain Adaptation for Pedestrian Detection
This paper addresses the problem of unsupervised domain adaptation on the task of pedestrian detection in crowded scenes.
Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams.
Kill Two Birds With One Stone: Boosting Both Object Detection Accuracy and Speed With adaptive Patch-of-Interest Composition
Object detection is an important yet challenging task in video understanding & analysis, where one major challenge lies in the proper balance between two contradictive factors: detection accuracy and detection speed.
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
Similar experiments with ResNet-50 reveal that even for a compact network, ThiNet can also reduce more than half of the parameters and FLOPs, at the cost of roughly 1$\%$ top-5 accuracy drop.
Ensemble of Part Detectors for Simultaneous Classification and Localization
Part-based representation has been proven to be effective for a variety of visual applications.
Learning Correspondence Structures for Person Re-identification
We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair.
Motion Segmentation via Global and Local Sparse Subspace Optimization
In this paper, we propose a new framework for segmenting feature-based moving objects under affine subspace model.
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene.
Picking Deep Filter Responses for Fine-Grained Image Recognition
Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.
Fractal Dimension Invariant Filtering and Its CNN-based Implementation
By adding a nonlinear post-processing step behind anisotropic filter banks, we demonstrate that the proposed filtering method is capable of preserving the local invariance of the fractal dimension of image.
A diffusion and clustering-based approach for finding coherent motions and understanding crowd scenes
These semantic regions can be used to recognize pre-defined activities in crowd scenes.
RIDE: Reversal Invariant Descriptor Enhancement
In many fine-grained object recognition datasets, image orientation (left/right) might vary from sample to sample.
Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-Based Shrinkage
Facing to the challenges of trajectory clustering, e. g., large variations within a cluster and ambiguities across clusters, we first introduce an adaptive multi-kernel-based estimation process to estimate the `shrunk' positions and speeds of trajectories' points.
Tree-based Visualization and Optimization for Image Collection
The visualization of an image collection is the process of displaying a collection of images on a screen under some specific layout requirements.
Person Re-identification with Correspondence Structure Learning
This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification.
Deep Spatial Pyramid: The Devil is Once Again in the Details
In this paper we show that by carefully making good choices for various detailed but important factors in a visual recognition framework using deep learning features, one can achieve a simple, efficient, yet highly accurate image classification system.
Macroblock Classification Method for Video Applications Involving Motions
We demonstrate that this low-computation-complexity method can efficiently catch the characteristics of the frame.
Group Event Detection with a Varying Number of Group Members for Video Surveillance
This paper presents a novel approach for automatic recognition of group activities for video surveillance applications.
Activity Recognition Using A Combination of Category Components And Local Models for Video Surveillance
This paper presents a novel approach for automatic recognition of human activities for video surveillance applications.
Improved Image Deblurring based on Salient-region Segmentation
Image deblurring techniques play important roles in many image processing applications.
A new network-based algorithm for human activity recognition in video
Based on this network, we further model people in the scene as packages while human activities can be modeled as the process of package transmission in the network.
A Heat-Map-based Algorithm for Recognizing Group Activities in Videos
In this paper, a new heat-map-based (HMB) algorithm is proposed for group activity recognition.
Intra-and-Inter-Constraint-based Video Enhancement based on Piecewise Tone Mapping
In this paper, we propose a new intra-and-inter-constraint-based video enhancement approach aiming to 1) achieve high intra-frame quality of the entire picture where multiple region-of-interests (ROIs) can be adaptively and simultaneously enhanced, and 2) guarantee the inter-frame quality consistencies among video frames.
Towards Good Practices for Action Video Encoding
High dimensional representations such as VLAD or FV have shown excellent accuracy in action recognition.
