Search Results for author:
Found 37 papers, 30 papers with code
Boundary-Aware Cascade Networks for Temporal Action Segmentation
To address these problems, we present a new boundary-aware cascade network by introducing two novel components.
Ranked #11 on
Action Segmentation
on GTEA
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
In this paper, we propose a novel module to explicitly extract motion and appearance information via a unifying operation.
Ranked #1 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(PSNR metric)
CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets
Our CoMAE presents a curriculum learning strategy to unify the two popular self-supervised representation learning algorithms: contrastive learning and masked image modeling.
MixFormer: End-to-End Tracking with Iterative Mixed Attention
Our core design is to utilize the flexibility of attention operations, and propose a Mixed Attention Module (MAM) for simultaneous feature extraction and target information integration.
Ranked #1 on
Visual Object Tracking
on LaSOT
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution
In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification
In the existing work, each point in the cloud may inevitably be selected as the neighbors of multiple aggregation centers, as all centers will gather neighbor features from the whole point cloud independently.
Ranked #26 on
3D Point Cloud Classification
on ScanObjectNN
Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution.
MixFormer: End-to-End Tracking with Iterative Mixed Attention
Our core design is to utilize the flexibility of attention operations, and propose a Mixed Attention Module (MAM) for simultaneous feature extraction and target information integration.
Ranked #4 on
Visual Object Tracking
on GOT-10k
Semi-Supervised Video Object Segmentation
Visual Object Tracking
Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection
Instead, in this paper, we present Temporal Perceiver, a general architecture with Transformer, offering a unified solution to the detection of arbitrary generic boundaries, ranging from shot-level, event-level, to scene-level GBDs.
Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning
By introducing dual path connections inspired by Dual Path Networks into EMSRDPN, it uses residual connections and dense connections in an integrated way in most network layers.
AdaDM: Enabling Normalization for Image Super-Resolution
We found that the standard deviation of the residual feature shrinks a lot after normalization layers, which causes the performance degradation in SR networks.
A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark
In this paper, we aim to present an in-depth study on few-shot video classification by making three contributions.
Mutual Supervision for Dense Object Detection
In this paper, we break the convention of the same training samples for these two heads in dense detectors and explore a novel supervisory paradigm, termed as Mutual Supervision (MuSu), to respectively and mutually assign training samples for the classification and regression head to ensure this consistency.
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
Instead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint embedding space.
Self Supervision to Distillation for Long-Tailed Visual Recognition
In this paper, we show that soft label can serve as a powerful solution to incorporate label correlation into a multi-stage training scheme for long-tailed recognition.
Ranked #32 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
Target Adaptive Context Aggregation for Video Scene Graph Generation
Specifically, we design an efficient method for frame-level VidSGG, termed as {\em Target Adaptive Context Aggregation Network} (TRACE), with a focus on capturing spatio-temporal context information for relation recognition.
CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation
Previous point cloud semantic segmentation networks use the same process to aggregate features from neighbors of the same category and different categories.
Ranked #1 on
Semantic Segmentation
on SYNTHIA
SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
Three-dimensional face dense alignment and reconstruction in the wild is a challenging problem as partial facial information is commonly missing in occluded and large pose face images.
Ranked #1 on
3D Face Reconstruction
on AFLW2000-3D
Anchor-based Plain Net for Mobile Image Super-Resolution
Along with the rapid development of real-world applications, higher requirements on the accuracy and efficiency of image super-resolution (SR) are brought forward.
MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
Spatio-temporal action detection is an important and challenging problem in video understanding.
MGSampler: An Explainable Sampling Strategy for Video Action Recognition
First, we present two different motion representations to enable us to efficiently distinguish the motion-salient frames from the background.
Target Transformed Regression for Accurate Tracking
Accurate tracking is still a challenging task due to appearance variations, pose and view changes, and geometric deformations of target in videos.
Ranked #1 on
Visual Object Tracking
on VOT2019
Relaxed Transformer Decoders for Direct Action Proposal Generation
Extensive experiments on THUMOS14 and ActivityNet-1. 3 benchmarks demonstrate the effectiveness of RTD-Net, on both tasks of temporal action proposal generation and temporal action detection.
Temporal Difference Networks for Action Recognition
To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition.
TDN: Temporal Difference Networks for Efficient Action Recognition
To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition.
Ranked #11 on
Action Recognition
on Something-Something V1
Residual Feature Distillation Network for Lightweight Image Super-Resolution
Thanks to FDC, we can rethink the information multi-distillation network (IMDN) and propose a lightweight and accurate SISR model called residual feature distillation network (RFDN).
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Context-Aware RCNN: A Baseline for Action Detection in Videos
In this work, we first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor, and thus higher resolution of actors contributes to better performance.
Fully Convolutional Online Tracking
To tackle this issue, we present the fully convolutional online tracking framework, coined as FCOT, and focus on enabling online learning for both classification and regression branches by using a target filter based tracking paradigm.
Actions as Moving Points
The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization.
Ranked #1 on
Action Detection
on UCF101-24
Simple and Lightweight Human Pose Estimation
Specifically, our LPN-50 can achieve 68. 7 in AP score on the COCO test-dev set, with only 2. 7M parameters and 1. 0 GFLOPs, while the inference speed is 17 FPS on an Intel i7-8700K CPU machine.
LIP: Local Importance-based Pooling
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption.
Ranked #134 on
Object Detection
on COCO minival
Dynamically Visual Disambiguation of Keyword-based Image Search
To address this issue, we present an adaptive multi-model framework that resolves polysemy by visual disambiguation.
Translate-to-Recognize Networks for RGB-D Scene Recognition
Empirically, we verify that this new semi-supervised setting is able to further enhance the performance of recognition network.
Learning Actor Relation Graphs for Group Activity Recognition
To this end, we propose to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors.
Ranked #3 on
Group Activity Recognition
on Collective Activity
StereoSnakes: Contour Based Consistent Object Extraction For Stereo Images
We also demonstrate in a few applications how our method can be used as a basic tool for stereo image editing.
