Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and cannot capture context information outside the bounding box. Recently, a few query-based action detectors are proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose a new one-stage sparse action detector, termed STMixer. STMixer is based on two core designs. First, we present a query-based adaptive feature sampling module, which endows our STMixer with the flexibility of mining a set of discriminative features from the entire spatiotemporal domain. Second, we devise a dual-branch feature mixing module, which allows our STMixer to dynamically attend to and mix video features along the spatial and the temporal dimension respectively for better feature decoding. Coupling these two designs with a video backbone yields an efficient end-to-end action detector. Without bells and whistles, our STMixer obtains the state-of-the-art results on the datasets of AVA, UCF101-24, and JHMDB.
University of Electronic Science and Technology of China（电子科技大学）；Activision Publishing, Inc.（动视出版公司）
There are a large number of methods for solving under-determined linear inverse problem. Many of them have very high time complexity for large datasets. We propose a new method called Two-Stage Sparse Representation (TSSR) to tackle this problem. We decompose the representing space of signals into two parts, the measurement dictionary and the sparsifying basis. The dictionary is designed to approximate a sub-Gaussian distribution to exploit its concentration property. We apply sparse coding to the signals on the dictionary in the first stage, and obtain the training and testing coefficients re…
Zhejiang University（浙江大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Most of the existing single-stage and two-stage 3D object detectors are anchor-based methods, while the efficient but challenging anchor-free single-stage 3D object detection is not well investigated. Recent studies on 2D object detection show that the anchor-free methods also are of great potential. However, the unordered and sparse properties of point clouds prevent us from directly leveraging the advanced 2D methods on 3D point clouds. We overcome this by converting the voxel-based sparse 3D feature volumes into the sparse 2D feature maps. We propose an attentive module to fit the sparse fe…
Tencent（腾讯）；The Chinese University of Hong Kong（香港中文大学）
We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a high recall with less computation compared with prior works. Then, PointsPool is applied for generating proposal features by transforming their interior point features from sparse expression to compact representation, which saves even more computation time. In box prediction, which is the second stage, …
Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland University（萨尔大学）；Saarbrücken Research Center for Visual Computing, Interaction and AI（萨尔布吕肯视觉计算、交互与人工智能研究中心）
Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate connections. Current gradient-based NAS methods commonly ignore the constraint of sparsity in the search phase, but project the optimized solution onto a sparse one by post-processing. As a result, the dense super-net for search is inefficient to train and has a gap with the projected architecture for evaluation. In this paper, we formulate neural architecture search as a sparse coding problem. We perform the differentiable search on a compressed lower-dimensional…
S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting
China University of Petroleum (East China)（中国石油大学（华东））；College of Computer Science and Technology（计算机科学与技术学院）；Qingdao Institute of Software（青岛软件学院）；Harbin Institute of Technology（哈尔滨工业大学）；Faculty of Computing（计算机学院）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Diffusion magnetic resonance imaging (dMRI) provides a unique tool for noninvasively probing the microstructure of the neuronal tissue. The NODDI model has been a popular approach to the estimation of tissue microstructure in many neuroscience studies. It represents the diffusion signals with three types of diffusion in tissue: intra-cellular, extra-cellular, and cerebrospinal fluid compartments. However, the original NODDI method uses a computationally expensive procedure to fit the model and could require a large number of diffusion gradients for accurate microstructure estimation, which may…
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of California, Berkeley（加州大学伯克利分校）；Tsinghua-Berkeley Shenzhen Institute（清华-伯克利深圳学院）；International Digital Economy Academy（国际数字经济研究院）；University of Electronic Science and Technology of China（电子科技大学）
Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret, and the learned representations lack clear structure. In this work, we make the explicit assumption that the image distribution is generated from a multi-stage sparse deconvolution. The corresponding inverse map, which we use as an encoder, is a multi-stage convolution sparse coding (CSC), with each stage obtained from unrolling an optimization algorithm for solving the corre…
Point2Insert: Video Object Insertion via Sparse Point Guidance
Institute of Artificial Intelligence, China Telecom (TeleAI)（人工智能研究院，中国电信（TeleAI））；Sun Yat-sen University（孙中山大学）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Fudan University（复旦大学）
ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学）；State Key Laboratory of Multimedia Information Processing, School of Electronic and Computer Engineering, Peking University（多媒体信息处理国家重点实验室，电子与计算机工程学院，北京大学）；Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University（王轩计算机技术研究所，多媒体信息处理国家重点实验室，北京大学）
In this paper, we propose a new multimodal image denoising approach to attenuate white Gaussian additive noise in a given image modality under the aid of a guidance image modality. The proposed coupled image denoising approach consists of two stages: coupled sparse coding and reconstruction. The first stage performs joint sparse transform for multimodal images with respect to a group of learned coupled dictionaries, followed by a shrinkage operation on the sparse representations. Then, in the second stage, the shrunken representations, together with coupled dictionaries, contribute to the reco…
Zhejiang University（浙江大学）；Shandong Medical Imaging Research Institute（山东医学影像研究所）；Shandong University（山东大学）；Lanzhou University（兰州大学）；Siemens Healthineers Ltd.（西门子医疗有限公司）；Beijing Institute of Technology（北京理工大学）
Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue microstructure based on biophysical models, which are complex and highly non-linear. Resolving microstructures with optimization techniques is prone to estimation errors and requires dense sampling in the q-space. Deep learning based approaches have been proposed to overcome these limitations. Motivated by the superior performance of the Transformer, in this work, we present a learning-based framework based on Transformer, namely, a Microstructure Estimation Transformer with Sparse Coding (METSC) for dMRI…
The recent thrust on digital agriculture (DA) has renewed significant research interest in the automated delineation of agricultural fields. Most prior work addressing this problem have focused on detecting medium to large fields, while there is strong evidence that around 40\% of the fields world-wide and 70% of the fields in Asia and Africa are small. The lack of adequate labeled images for small fields, huge variations in their color, texture, and shape, and faint boundary lines separating them make it difficult to develop an end-to-end learning model for detecting such fields. Hence, in th…
Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a one-to-one label assignment scheme, where the Hungarian algorithm is applied to match only one positive sample for each ground truth. Such one-to-one assignment may not be optimal for the matching between the learned proposal boxes and ground truths. To address this problem, we propose dynamic label assignment (DLA) based on the optimal transport algorithm to…
Shanghai Jiao Tong University（上海交通大学）；University of Sydney（悉尼大学）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院瑞金医院）
Motion estimation is a fundamental step in dynamic medical image processing for the assessment of target organ anatomy and function. However, existing image-based motion estimation methods, which optimize the motion field by evaluating the local image similarity, are prone to produce implausible estimation, especially in the presence of large motion. In this study, we provide a novel motion estimation framework of Dense-Sparse-Dense (DSD), which comprises two stages. In the first stage, we process the raw dense image to extract sparse landmarks to represent the target organ anatomical topology…
DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-View
School of Electrical and Computer Engineering, Cornell University（电气与计算机工程系，康奈尔大学）；Sibley School of Mechanical and Aerospace Engineering, Cornell University（机械与航空航天工程系，康奈尔大学）；School of Biological and Environmental Engineering, Cornell University（生物与环境工程系，康奈尔大学）；School of Integrative Plant Science, Cornell University（整合植物科学系，康奈尔大学）
Durham University（杜伦大学）；NHL Stenden University of Applied Sciences（NHL斯坦登应用科学大学）
Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature detectors however either give sparse, non uniform point clouds (resulting in flow inaccuracies) or lack the efficiency for frame-rate real-time applications. In this work we use the novel Dense Gradient Based Features (DeGraF) as the input to a sparse-to-dense optical flow scheme. This consists of three stages: 1) efficient detection of uniformly distributed Dense Gradient Based Features (DeGraF); 2) feature tracking …
Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications
School of Computer Engineering, Iran University of Science and Technology（伊朗科学技术大学计算机工程学院）；George Mason University Department of Computer Science（乔治·梅奥大学计算机科学系）
Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）
Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twists, such as multi-stage features, connections that skip layers to integrate global shape information with local distinctive motif information, and an unsupervised method based on convolutional sparse coding to pre-train the filters at each stage.
Accurate detection of individual intake gestures is a key step towards automatic dietary monitoring. Both inertial sensor data of wrist movements and video data depicting the upper body have been used for this purpose. The most advanced approaches to date use a two-stage approach, in which (i) frame-level intake probabilities are learned from the sensor data using a deep neural network, and then (ii) sparse intake events are detected by finding the maxima of the frame-level probabilities. In this study, we propose a single-stage approach which directly decodes the probabilities learned from se…
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（计算机科学与技术系，人工智能研究所，BNRist中心，THBI实验室，清华-博世联合机器学习中心，清华大学）；Institute for Interdisciplinary Information Sciences, Tsinghua University（交叉信息学院，清华大学）；EECS, University of California, Berkeley（电子工程与计算机科学系，加州大学伯克利分校）
