Search Results for author:
Found 140 papers, 46 papers with code
Kernel Least Mean Square with Adaptive Kernel Size
Kernel adaptive filters (KAF) are a class of powerful nonlinear filters developed in Reproducing Kernel Hilbert Space (RKHS).
Salient Object Detection: A Discriminative Regional Feature Integration Approach
Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score.
Generalized Correntropy for Robust Adaptive Filtering
In this work, we propose a generalized correntropy that adopts the generalized Gaussian density (GGD) function as the kernel (not necessarily a Mercer kernel), and present some important properties.
Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification
We follow the learning-to-rank methodology and learn a similarity function to maximize the difference between the similarity scores of matched and unmatched images for a same person.
Saturation-Preserving Specular Reflection Separation
Specular reflection generally decreases the saturation of surface colors, which will be possibly confused with other colors that have the same hue but lower saturation.
Contour Guided Hierarchical Model for Shape Matching
For the purpose, we divide the shape template into overlapped parts and model the matching through a part-based layered structure that uses the latent variable to constrain parts' deformation.
Illumination Robust Color Naming via Label Propagation
In this paper we address the problem of inferring the color composition of the intrinsic reflectance of objects, where the shadows and highlights may change the observed color dramatically.
Correntropy Maximization via ADMM - Application to Robust Hyperspectral Unmixing
In hyperspectral images, some spectral bands suffer from low signal-to-noise ratio due to noisy acquisition and atmospheric effects, thus requiring robust techniques for the unmixing problem.
Counting Grid Aggregation for Event Retrieval and Recognition
Event retrieval and recognition in a large corpus of videos necessitates a holistic fixed-size visual representation at the video clip level that is comprehensive, compact, and yet discriminative.
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.
Similarity Learning With Spatial Constraints for Person Re-Identification
We therefore learn a novel similarity function, which consists of multiple sub-similarity measurements with each taking in charge of a subregion.
Kernel Risk-Sensitive Loss: Definition, Properties and Application to Robust Adaptive Filtering
Nonlinear similarity measures defined in kernel space, such as correntropy, can extract higher-order statistics of data and offer potentially significant performance improvement over their linear counterparts especially in non-Gaussian signal processing and machine learning.
Robust Learning with Kernel Mean p-Power Error Loss
Correntropy is a second order statistical measure in kernel space, which has been successfully applied in robust learning and signal processing.
Brain Inspired Cognitive Model with Attention for Self-Driving Cars
Perception-driven approach and end-to-end system are two major vision-based frameworks for self-driving cars.
Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network
To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed.
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
Rather than re-positioning the skeletons based on a human defined prior criterion, we design a view adaptive recurrent neural network (RNN) with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end.
Ranked #6 on
Skeleton Based Action Recognition
on SYSU 3D
Single Image Super Resolution - When Model Adaptation Matters
The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors.
Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach
Experiments show that our unsupervised approach is efficient and robust for detecting drivable area for self-driving cars.
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.
ER3: A Unified Framework for Event Retrieval, Recognition and Recounting
We develop a unified framework for complex event retrieval, recognition and recounting.
Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
The proposed method can take full advantages of the structured distance relationships among these training samples, with the constructed complete graph.
Associations among Image Assessments as Cost Functions in Linear Decomposition: MSE, SSIM, and Correlation Coefficient
Moreover, for a target vector, the ratio of the corresponding affine parameters in the MSE-based linear decomposition scheme and the SSIM-based scheme is a constant, which is just the value of PCC between the target vector and its estimated vector.
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 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.
Quantized Minimum Error Entropy Criterion
Comparing with traditional learning criteria, such as mean square error (MSE), the minimum error entropy (MEE) criterion is superior in nonlinear and non-Gaussian signal processing and machine learning.
A Novel Brain Decoding Method: a Correlation Network Framework for Revealing Brain Connections
Analyzing the correlations of collected data from human brain activities and representing activity patterns are two problems in brain decoding based on functional magnetic resonance imaging (fMRI) signals.
Augmented Space Linear Model
In this paper, we propose a linear model called Augmented Space Linear Model (ASLM), which uses the full joint space of input and desired signal as the projection space and approaches the performance of nonlinear models.
Fully Convolutional Grasp Detection Network with Oriented Anchor Box
The feature extractor is a deep convolutional neural network.
Feature Selective Small Object Detection via Knowledge-based Recurrent Attentive Neural Network
At present, the performance of deep neural network in general object detection is comparable to or even surpasses that of human beings.
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints in a learning based data driven manner.
Ranked #1 on
Skeleton Based Action Recognition
on UWA3D
Kernelized Subspace Pooling for Deep Local Descriptors
Experimental results on several patch matching benchmarks show that our method outperforms the state-of-the-arts significantly.
Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks
We built a new video dataset of tasks, intentions, and attention.
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.
Adding Attentiveness to the Neurons in Recurrent Neural Networks
We propose adding a simple yet effective Element-wiseAttention Gate (EleAttG) to an RNN block (e. g., all RNN neurons in a network layer) that empowers the RNN neurons to have the attentiveness capability.
Ranked #98 on
Skeleton Based Action Recognition
on NTU RGB+D
ROI-based Robotic Grasp Detection for Object Overlapping Scenes
Experimental results demonstrate that ROI-GD performs much better in object overlapping scenes and at the meantime, remains comparable with state-of-the-art grasp detection algorithms on Cornell Grasp Dataset and Jacquard Dataset.
Robotics
Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification
The reason is that the bilinear feature matrix is sensitive to the magnitudes and correlations of local CNN feature elements which can be measured by its singular values.
Fine-Grained Image Classification
Fine-Grained Visual Recognition
+1
Transductive Semi-Supervised Deep Learning using Min-Max Features
In this paper, we propose Transductive Semi-Supervised Deep Learning (TSSDL) method that is effective for training Deep Convolutional Neural Network (DCNN) models.
A Real-time Robotic Grasp Approach with Oriented Anchor Box
The main component of our approach is a grasp detection network with oriented anchor boxes as detection priors.
Robotics
A Multi-task Convolutional Neural Network for Autonomous Robotic Grasping in Object Stacking Scenes
Autonomous robotic grasping plays an important role in intelligent robotics.
Robotics
Consistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition
We propose a Consistency-aware Selective Fusion (CSF) to integrate the pairwise orders into a globally consistent order.
SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism.
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data.
Ranked #1 on
Skeleton Based Action Recognition
on SYSU 3D
Hindsight Trust Region Policy Optimization
We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle the challenge of sparse rewards.
An encoding framework with brain inner state for natural image identification
The framework comprises two parts: forward encoding model that deals with visual stimuli and inner state model that captures influence from intrinsic connections in the brain.
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
For an RNN block, an EleAttG is used for adaptively modulating the input by assigning different levels of importance, i. e., attention, to each element/dimension of the input.
Ranked #3 on
Skeleton Based Action Recognition
on SYSU 3D
Learnable Tree Filter for Structure-preserving Feature Transform
To this end, tree filtering modules are embedded to formulate a unified framework for semantic segmentation.
BEYOND SUPERVISED LEARNING: RECOGNIZING UNSEEN ATTRIBUTE-OBJECT PAIRS WITH VISION-LANGUAGE FUSION AND ATTRACTOR NETWORKS
This paper handles a challenging problem, unseen attribute-object pair recognition, which asks a model to simultaneously recognize the attribute type and the object type of a given image while this attribute-object pair is not included in the training set.
Visual Semantic SLAM with Landmarks for Large-Scale Outdoor Environment
Semantic SLAM is an important field in autonomous driving and intelligent agents, which can enable robots to achieve high-level navigation tasks, obtain simple cognition or reasoning ability and achieve language-based human-robot-interaction.
REGNet: REgion-based Grasp Network for End-to-end Grasp Detection in Point Clouds
Reliable robotic grasping in unstructured environments is a crucial but challenging task.
Robotics
Compositional Generalization by Learning Analytical Expressions
Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily.
Traffic Agent Trajectory Prediction Using Social Convolution and Attention Mechanism
In this paper, we propose a model to predict the trajectories of target agents around an autonomous vehicle.
A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning
Using a gating mechanism that discriminates the unseen samples from the seen samples can decompose the GZSL problem to a conventional Zero-Shot Learning (ZSL) problem and a supervised classification problem.
Conditional Uncorrelation and Efficient Non-approximate Subset Selection in Sparse Regression
By the proposed method, the computational complexity is reduced from $O(\frac{1}{6}{k^3}+mk^2+mkd)$ to $O(\frac{1}{6}{k^3}+\frac{1}{2}mk^2)$ for each candidate subset in sparse regression.
Learning to Infer Unseen Attribute-Object Compositions
The composition recognition of unseen attribute-object is critical to make machines learn to decompose and compose complex concepts like people.
Multi-agent Policy Optimization with Approximatively Synchronous Advantage Estimation
General methods for policy based multi-agent reinforcement learning to solve the challenge introduce differentiate value functions or advantage functions for individual agents.
End-to-End Object Detection with Fully Convolutional Network
Mainstream object detectors based on the fully convolutional network has achieved impressive performance.
Fine-Grained Dynamic Head for Object Detection
To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation.
Rethinking Learnable Tree Filter for Generic Feature Transform
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation.
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.
Practical Order Attack in Deep Ranking
The objective of this paper is to formalize and practically implement a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order of a selected set of candidates according to a permutation vector predefined by the attacker, with only limited interference to other unrelated candidates.
Towards Building A Group-based Unsupervised Representation Disentanglement Framework
We then propose a model, based on existing VAE-based methods, to tackle the unsupervised learning problem of the framework.
A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN
In autonomous driving, perceiving the driving behaviors of surrounding agents is important for the ego-vehicle to make a reasonable decision.
Practical Relative Order Attack in Deep Ranking
In this paper, we formulate a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates.
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
REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
In this paper, we present a new dataset named REGRAD for the learning of relationships among objects and grasps.
Adversarial Attack and Defense in Deep Ranking
In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.
Video Imprint
In the proposed framework, a dedicated feature alignment module is incorporated for redundancy removal across frames to produce the tensor representation, i. e., the video imprint.
Learning Algebraic Recombination for Compositional Generalization
In this paper, we propose LeAR, an end-to-end neural model to learn algebraic recombination for compositional generalization.
Ranked #2 on
Semantic Parsing
on CFQ
Probabilistic Human Motion Prediction via A Bayesian Neural Network
The experimental results show that our approach makes the interaction more efficient and safer.
X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering
In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the problem.
Enriching Local and Global Contexts for Temporal Action Localization
We explore two existing models to be the P-Net in our experiments.
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.
Model-based Decision Making with Imagination for Autonomous Parking
The proposed algorithm consists of three parts: an imaginative model for anticipating results before parking, an improved rapid-exploring random tree (RRT) for planning a feasible trajectory from a given start point to a parking lot, and a path smoothing module for optimizing the efficiency of parking tasks.
LGD: Label-guided Self-distillation for Object Detection
Instead, we generate an instructive knowledge based only on student representations and regular labels.
Foreground-attention in neural decoding: Guiding Loop-Enc-Dec to reconstruct visual stimulus images from fMRI
Inspired by the mechanism of human visual attention, in this paper, we propose a novel method of reconstructing visual stimulus images, which first decodes the distribution of visual attention from fMRI, and then reconstructs the visual images guided by visual attention.
Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer
The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery.
Instance-Conditional Knowledge Distillation for Object Detection
Knowledge distillation has shown great success in classification, however, it is still challenging for detection.
LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering
Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content.
Co-evolution Transformer for Protein Contact Prediction
These methods generally derive coevolutionary features by aggregating the learned residue representations from individual sequences with equal weights, which is inconsistent with the premise that residue co-evolutions are a reflection of collective covariation patterns of numerous homologous proteins.
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.
Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding
Trajectories obtained from object detection and tracking are inevitably noisy, which could cause serious forecasting errors to predictors built on ground truth trajectories.
Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models
This motivates us to propose input-tuning, which fine-tunes both the continuous prompts and the input representations, leading to a more effective way to adapt unfamiliar inputs to frozen PLMs.
Test-time Batch Normalization
Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift.
Visual Concepts Tokenization
We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts.
Social Interpretable Tree for Pedestrian Trajectory Prediction
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications.
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.
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference.
Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering
In this paper, we aim to improve input robustness from an information bottleneck perspective when adapting pretrained VLMs to the downstream VQA task.
Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios
In this paper, we propose a lightweight system, RDS-SLAM, based on ORB-SLAM2, which can accurately estimate poses and build semantic maps at object level for dynamic scenarios in real time using only one commonly used Intel Core i7 CPU.
Could Giant Pretrained Image Models Extract Universal Representations?
In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition.
Ranked #3 on
Action Recognition In Videos
on Kinetics-400
Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
To ensure optimal consistency, the optimal node is required to be the unique STN.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
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.
Object-fabrication Targeted Attack for Object Detection
Evaluation results demonstrate that, the proposed object-fabrication targeted attack mode and the corresponding targeted feature space attack method show significant improvements in terms of image-specific attack, universal performance and generalization capability, compared with the previous targeted attack for object detection.
DETR Does Not Need Multi-Scale or Locality Design
This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based detectors that reintroduce architectural inductive biases of multi-scale and locality into the decoder.
Inverse Compositional Learning for Weakly-supervised Relation Grounding
In this study, we introduce a novel approach called inverse compositional learning (ICL) for weakly-supervised video relation grounding.
Dynamic Grained Encoder for Vision Transformers
Specifically, we propose a Dynamic Grained Encoder for vision transformers, which can adaptively assign a suitable number of queries to each spatial region.
Does Deep Learning Learn to Abstract? A Systematic Probing Framework
Abstraction is a desirable capability for deep learning models, which means to induce abstract concepts from concrete instances and flexibly apply them beyond the learning context.
BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding
Our experiments show that this combination can boost the decoding model's performance on certain tasks like fMRI-text matching and fMRI-to-image generation.
MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering
In this paper, we propose MixPHM, a redundancy-aware parameter-efficient tuning method that outperforms full finetuning in low-resource VQA.
Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys
Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits.
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.
MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes
Manipulation relationship detection (MRD) aims to guide the robot to grasp objects in the right order, which is important to ensure the safety and reliability of grasping in object stacked scenes.
Quadric Representations for LiDAR Odometry, Mapping and Localization
Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes and achieve high accuracy in autonomous driving tasks.
How Do In-Context Examples Affect Compositional Generalization?
Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence.
Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors
Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions.
Skill-Based Few-Shot Selection for In-Context Learning
Few-shot selection -- selecting appropriate examples for each test instance separately -- is important for in-context learning.
Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization
In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization.
Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning
Growing interest in autonomous driving (AD) and intelligent vehicles (IVs) is fueled by their promise for enhanced safety, efficiency, and economic benefits.
When and Why Momentum Accelerates SGD:An Empirical Study
In the comparison of SGDM and SGD with the same effective learning rate and the same batch size, we observe a consistent pattern: when $\eta_{ef}$ is small, SGDM and SGD experience almost the same empirical training losses; when $\eta_{ef}$ surpasses a certain threshold, SGDM begins to perform better than SGD.
LongNet: Scaling Transformers to 1,000,000,000 Tokens
Scaling sequence length has become a critical demand in the era of large language models.
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.
FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene
It has long been an ill-posed problem to predict absolute depth maps from single images in real (unseen) indoor scenes.
DETR Doesn't Need Multi-Scale or Locality Design
This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based detectors that reintroduce architectural inductive biases of multi-scale and locality into the decoder.
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
We introduce a highly performant 3D object detector for point clouds using the DETR framework.
Ranked #2 on
3D Object Detection
on ScanNetV2
Complementing Onboard Sensors with Satellite Map: A New Perspective for HD Map Construction
To enable better integration of satellite maps with existing methods, we propose a hierarchical fusion module, which includes feature-level fusion and BEV-level fusion.
InteractionNet: Joint Planning and Prediction for Autonomous Driving with Transformers
Planning and prediction are two important modules of autonomous driving and have experienced tremendous advancement recently.
Ranked #9 on
CARLA longest6
on CARLA
Generalization error bounds for iterative learning algorithms with bounded updates
This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniques.
Breaking through the learning plateaus of in-context learning in Transformer
To study the mechanism behind the learning plateaus, we conceptually seperate a component within the model's internal representation that is exclusively affected by the model's weights.
Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
Orbital-free density functional theory (OFDFT) is a quantum chemistry formulation that has a lower cost scaling than the prevailing Kohn-Sham DFT, which is increasingly desired for contemporary molecular research.
Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching
Current image-based keypoint detection methods for animal (including human) bodies and faces are generally divided into full-supervised and few-shot class-agnostic approaches.
G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data
This paper investigates a unified task of monocular depth inference, which infers high-quality depth maps from all kinds of input raw data from various robots in unseen scenes.
Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity
Recently, Arjevani et al. [1] established a lower bound of iteration complexity for the first-order optimization under an $L$-smooth condition and a bounded noise variance assumption.
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.
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.
IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance
Among existing Neural Architecture Search methods, DARTS is known for its efficiency and simplicity.
An automated framework for brain vessel centerline extraction from CTA images
In this paper, we consider automatic lumen segmentation generation without additional annotation effort by physicians and more effective use of the generated lumen segmentation for improved centerline extraction performance.
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Disentangled representation learning strives to extract the intrinsic factors within observed data.
Dual-Space Optimization: Improved Molecule Sequence Design by Latent Prompt Transformer
Designing molecules with desirable properties, such as drug-likeliness and high binding affinities towards protein targets, is a challenging problem.
From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs
In this work, we introduce a novel tool invocation pipeline designed to control massive real-world APIs.
Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection
3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding.
Common 7B Language Models Already Possess Strong Math Capabilities
This paper shows that the LLaMA-2 7B model with common pre-training already exhibits strong mathematical abilities, as evidenced by its impressive accuracy of 97. 7% and 72. 0% on the GSM8K and MATH benchmarks, respectively, when selecting the best response from 256 random generations.
See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRI
Our model integrates a high-level perception decoding pipeline and a pixel-wise reconstruction pipeline guided by high-level perceptions, simulating bottom-up and top-down processes in neuroscience.
Exploring Hardware Friendly Bottleneck Architecture in CNN for Embedded Computing Systems
We deploy our L-Mobilenet model to ZYNQ embedded platform for fully evaluating the performance of our design.
Self-Consistency Training for Hamiltonian Prediction
This merit addresses the data scarcity difficulty, and distinguishes the task from other property prediction formulations with unique benefits: (1) self-consistency training enables the model to be trained on a large amount of unlabeled data, hence substantially enhances generalization; (2) self-consistency training is more efficient than labeling data with DFT for supervised training, since it is an amortization of DFT calculation over a set of molecular structures.
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.
