Search Results for author:
Found 131 papers, 76 papers with code
Aligning Instruction Tuning with Pre-training
Instruction tuning enhances large language models (LLMs) to follow human instructions across diverse tasks, relying on high-quality datasets to guide behavior.
Practical Continual Forgetting for Pre-trained Vision Models
(ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal.
LayerAnimate: Layer-specific Control for Animation
In this paper, we introduce LayerAnimate, a novel architectural approach that enhances fine-grained control over individual animation layers within a video diffusion model, allowing users to independently manipulate foreground and background elements in distinct layers.
DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers
World model-based searching and planning are widely recognized as a promising path toward human-level physical intelligence.
FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes
We propose FreeSim, a camera simulation method for autonomous driving.
OOD-HOI: Text-Driven 3D Whole-Body Human-Object Interactions Generation Beyond Training Domains
Generating realistic 3D human-object interactions (HOIs) from text descriptions is a active research topic with potential applications in virtual and augmented reality, robotics, and animation.
SimCMF: A Simple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality
To this end, this work presents a simple and effective framework, SimCMF, to study an important problem: cross-modal fine-tuning from vision foundation models trained on natural RGB images to other imaging modalities of different physical properties (e. g., polarization).
Revisiting Marr in Face: The Building of 2D--2.5D--3D Representations in Deep Neural Networks
By injecting graphics probes into neural networks, and analyzing their behavior in reconstructing images, we find that DNNs initially encode images as 2D representations in low-level layers, and finally construct 3D representations in high-level layers.
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
Bird's-eye-view (BEV) map layout estimation requires an accurate and full understanding of the semantics for the environmental elements around the ego car to make the results coherent and realistic.
CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis.
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
By publishing and maintaining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.
FreeVS: Generative View Synthesis on Free Driving Trajectory
Moreover, we propose two new challenging benchmarks tailored to driving scenes, which are novel camera synthesis and novel trajectory synthesis, emphasizing the freedom of viewpoints.
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i. e., math, coding, commonsense reasoning).
MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
Besides, all evaluation metrics of our MTU-Bench are based on the prediction results and the ground truth without using any GPT or human evaluation metrics.
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Driving world models have gained increasing attention due to their ability to model complex physical dynamics.
Reconstructive Visual Instruction Tuning
This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals.
MIO: A Foundation Model on Multimodal Tokens
In this paper, we introduce MIO, a novel foundation model built on multimodal tokens, capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
Therefore, we introduce the Hierarchical Long Text Generation Benchmark (HelloBench), a comprehensive, in-the-wild, and open-ended benchmark to evaluate LLMs' performance in generating long text.
OmniBench: Towards The Future of Universal Omni-Language Models
Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities.
SimMAT: Exploring Transferability from Vision Foundation Models to Any Image Modality
To this end, this work presents a simple and effective framework SimMAT to study an open problem: the transferability from vision foundation models trained on natural RGB images to other image modalities of different physical properties (e. g., polarization).
Enhancing Sound Source Localization via False Negative Elimination
To address this issue, we propose a novel audio-visual learning framework which is instantiated with two individual learning schemes: self-supervised predictive learning (SSPL) and semantic-aware contrastive learning (SACL).
CityX: Controllable Procedural Content Generation for Unbounded 3D Cities
With the surge of embodied intelligence, recent years have witnessed an increasing presence of physical agents in urban areas, such as autonomous vehicles and delivery robots.
General Geometry-aware Weakly Supervised 3D Object Detection
However, the annotation of large-scale 3D datasets requires significant human effort.
Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation
The scarcity of large-scale 3D-text paired data poses a great challenge on open vocabulary 3D scene understanding, and hence it is popular to leverage internet-scale 2D data and transfer their open vocabulary capabilities to 3D models through knowledge distillation.
Monocular Occupancy Prediction for Scalable Indoor Scenes
With a dataset size 40 times larger than the NYUv2 dataset, it facilitates future scalable research in indoor scene analysis.
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
Inspired by the recent advances of state space models (SSMs), we present a Voxel SSM, termed as Voxel Mamba, which employs a group-free strategy to serialize the whole space of voxels into a single sequence.
Enhancing End-to-End Autonomous Driving with Latent World Model
Specifically, our framework \textbf{LAW} uses a LAtent World model to predict future latent features based on the predicted ego actions and the latent feature of the current frame.
Trim 3D Gaussian Splatting for Accurate Geometry Representation
Furthermore, our experimental and theoretical analyses reveal that a relatively small Gaussian scale is a non-negligible factor in representing and optimizing the intricate details.
Towards Flexible Interactive Reflection Removal with Human Guidance
However, incorporating the raw user guidance naively into the existing reflection removal network does not result in performance gains.
Learning Object-Centric Representation via Reverse Hierarchy Guidance
Object-Centric Learning (OCL) seeks to enable Neural Networks to identify individual objects in visual scenes, which is crucial for interpretable visual comprehension and reasoning.
StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
The effect of the design of each component is still unclear.
A Survey on Personalized Content Synthesis with Diffusion Models
This paper offers a comprehensive survey of PCS, with a particular focus on the diffusion models.
Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
Image Anomaly Detection has been a challenging task in Computer Vision field.
Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond
General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems.
MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets
Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance.
Robust Depth Enhancement via Polarization Prompt Fusion Tuning
Existing depth sensors are imperfect and may provide inaccurate depth values in challenging scenarios, such as in the presence of transparent or reflective objects.
CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians
The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS).
Enhancing Visual Continual Learning with Language-Guided Supervision
Existing methods commonly utilize the one-hot labels and randomly initialize the classifier head.
SceneX: Procedural Controllable Large-scale Scene Generation
Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation.
Generative Active Learning for Image Synthesis Personalization
The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept.
Continual Forgetting for Pre-trained Vision Models
(i) For unwanted knowledge, efficient and effective deleting is crucial.
Open-world Machine Learning: A Review and New Outlooks
This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm, to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
MemoNav: Working Memory Model for Visual Navigation
Subsequently, a graph attention module encodes the retained STM and the LTM to generate working memory (WM) which contains the scene features essential for efficient navigation.
DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer
We suspect this is due to a shortage of paired audio-4D data, which is crucial for the Transformer to effectively perform as a denoiser within the Diffusion framework.
SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition
3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed.
MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
Thus, MixSup leverages massive coarse cluster-level labels to learn semantics and a few expensive box-level labels to learn accurate poses and shapes.
Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images.
FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes
Indoor scene generation has attracted significant attention recently as it is crucial for applications of gaming, virtual reality, and interior design.
HardMo: A Large-Scale Hardcase Dataset for Motion Capture
Empirically we find that the prediction failure in dance and martial arts is mainly characterized by the misalignment of hand-wrist and foot-ankle.
RCL: Reliable Continual Learning for Unified Failure Detection
Concretely we identify the failure of simply integrating learning objectives of misclassification and OOD detection and show the potential of sequence learning.
Pareto-based Multi-Objective Recommender System with Forgetting Curve
Considering recency effect in memories, we propose a forgetting model based on Ebbinghaus Forgetting Curve to cope with negative feedback.
Bootstrap Masked Visual Modeling via Hard Patches Mining
To empower the model as a teacher, we propose Hard Patches Mining (HPM), predicting patch-wise losses and subsequently determining where to mask.
Compositional Inversion for Stable Diffusion Models
It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space.
GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives
With these region-specific narratives (partial observations) and a holistic narrative (global observation) for an image, a large language model (LLM) performs the relationship reasoning to synthesize an accurate and comprehensive scene graph.
Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
In autonomous driving, predicting future events in advance and evaluating the foreseeable risks empowers autonomous vehicles to better plan their actions, enhancing safety and efficiency on the road.
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
For the more challenging settings of relation-involved open vocabulary SGG, the proposed approach integrates relation-aware pretraining utilizing image-caption data and retains visual-concept alignment through knowledge distillation.
Visual Commonsense based Heterogeneous Graph Contrastive Learning
Specifically, our model contains two key components: the Commonsense-based Contrastive Learning and the Graph Relation Network.
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters.
Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation
One-shot domain adaptation methods attempt to overcome these challenges by transferring the pre-trained source model to the target domain using only one target data.
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident.
Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization
On top of the proposed AnoCLIP, we further introduce a test-time adaptation (TTA) mechanism to refine visual anomaly localization results, where we optimize a lightweight adapter in the visual encoder using AnoCLIP's pseudo-labels and noise-corrupted tokens.
FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels
Consequently, we develop a suite of components to complement the virtual voxel concept, including a virtual voxel encoder, a virtual voxel mixer, and a virtual voxel assignment strategy.
DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation
The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes.
Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion
Radar is ubiquitous in autonomous driving systems due to its low cost and good adaptability to bad weather.
DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
Considering this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net), which explicitly models ambiguous snippets and discriminative snippets with well-designed connections, preventing the transmission of ambiguous information and enhancing the discriminability of snippet-level representations.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
BMAD: Benchmarks for Medical Anomaly Detection
However, there is a lack of a universal and fair benchmark for evaluating AD methods on medical images, which hinders the development of more generalized and robust AD methods in this specific domain.
Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding
The framework of visually-guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing.
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
In this work, we address this limitation by studying camera-based 3D panoptic segmentation, aiming to achieve a unified occupancy representation for camera-only 3D scene understanding.
Tracking Objects with 3D Representation from Videos
In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space.
Weakly Supervised 3D Object Detection with Multi-Stage Generalization
We devise the DoubleClustering algorithm to obtain object clusters from reconstructed scene-level points, and further enhance the model's detection capabilities by developing three stages of generalization: progressing from complete to partial, static to dynamic, and close to distant.
Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation
A common practice is to select the highly confident predictions as the pseudo-ground-truths for each pixel, but it leads to a problem that most pixels may be left unused due to their unreliability.
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions.
Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation
To this end, we propose T2S-DA, which we interpret as a form of pulling Target to Source for Domain Adaptation, encouraging the model in learning similar cross-domain features.
Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection
Data and model are the undoubtable two supporting pillars for LiDAR object detection.
Fully Sparse Fusion for 3D Object Detection
In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture.
Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection
Drawing inspiration from this, we propose a high-performance offline detector in a track-centric perspective instead of the conventional object-centric perspective.
Hard Patches Mining for Masked Image Modeling
We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task.
3D Video Object Detection with Learnable Object-Centric Global Optimization
We explore long-term temporal visual correspondence-based optimization for 3D video object detection in this work.
Learnable Graph Matching: A Practical Paradigm for Data Association
Data association is at the core of many computer vision tasks, e. g., multiple object tracking, image matching, and point cloud registration.
Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images
The function of constructing the hierarchy of objects is important to the visual process of the human brain.
Sharpness-Aware Gradient Matching for Domain Generalization
In this paper, we present two conditions to ensure that the model could converge to a flat minimum with a small loss, and present an algorithm, named Sharpness-Aware Gradient Matching (SAGM), to meet the two conditions for improving model generalization capability.
A Survey of Deep Visual Cross-Domain Few-Shot Learning
Research into Cross-Domain Few-Shot (CDFS) has emerged to address this issue, forming a more challenging and realistic setting.
Blind Video Deflickering by Neural Filtering with a Flawed Atlas
Prior work usually requires specific guidance such as the flickering frequency, manual annotations, or extra consistent videos to remove the flicker.
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR.
Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models
The ability to discover abstract physical concepts and understand how they work in the world through observing lies at the core of human intelligence.
Fairly Adaptive Negative Sampling for Recommendations
Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i. e., clicked by a user) and negative items (i. e., obtained by negative sampling).
FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection
The transformation of features from 2D perspective space to 3D space is essential to multi-view 3D object detection.
Super Sparse 3D Object Detection
To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD.
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation
Moreover, we find that the image feature maps' resolution in the cross-attention module has a limited effect on the final performance.
Ranked #6 on
Bird's-Eye View Semantic Segmentation
on nuScenes
FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation
Without introducing any external supervision and human priors, the proposed FPR effectively suppresses wrong activations from the background objects.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow
Surrogate gradient (SG) is one of the most effective approaches for training spiking neural networks (SNNs).
Extracting Semantic Knowledge from GANs with Unsupervised Learning
Second, we train image-to-image translation networks on the synthesized datasets, enabling semantic-conditional image synthesis without human annotations.
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset.
Ranked #5 on
3D Object Detection
on Rope3D
RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection
While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed SR image should enable better SR reconstruction for its similar LR images when it is referred to as.
Pointly-Supervised Panoptic Segmentation
In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation.
4D Unsupervised Object Discovery
In this paper, we propose 4D unsupervised object discovery, jointly discovering objects from 4D data -- 3D point clouds and 2D RGB images with temporal information.
MemoNav: Selecting Informative Memories for Visual Navigation
To address this limitation, we present the MemoNav, a novel memory mechanism for image-goal navigation, which retains the agent's informative short-term memory and long-term memory to improve the navigation performance on a multi-goal task.
Pro-tuning: Unified Prompt Tuning for Vision Tasks
To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.
Fully Sparse 3D Object Detection
To enable efficient long-range LiDAR-based object detection, we build a fully sparse 3D object detector (FSD).
Densely Constrained Depth Estimator for Monocular 3D Object Detection
So these methods only use a small number of projection constraints and produce insufficient depth candidates, leading to inaccurate depth estimation.
Implicit Sample Extension for Unsupervised Person Re-Identification
Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy.
Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes
Sound source localization in visual scenes aims to localize objects emitting the sound in a given image.
Sparse Instance Activation for Real-Time Instance Segmentation
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation.
Ranked #7 on
Real-time Instance Segmentation
on MSCOCO
HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network
Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception.
DATA: Domain-Aware and Task-Aware Self-supervised Learning
However, due to the high training costs and the unconsciousness of downstream usages, most self-supervised learning methods lack the capability to correspond to the diversities of downstream scenarios, as there are various data domains, different vision tasks and latency constraints on models.
The Devil Is in the Details: Window-based Attention for Image Compression
Inspired by recent progresses of Vision Transformer (ViT) and Swin Transformer, we found that combining the local-aware attention mechanism with the global-related feature learning could meet the expectation in image compression.
Ranked #1 on
Image Compression
on kodak
Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks
Moreover, through experiments we show that discrete language representation has several advantages compared with continuous feature representation, from the aspects of interpretability, generalization, and robustness.
Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer
To remedy this problem, we propose an interesting and challenging cross-domain few-shot semantic segmentation task, where the training and test tasks perform on different domains.
Continual Stereo Matching of Continuous Driving Scenes With Growing Architecture
The deep stereo models have achieved state-of-the-art performance on driving scenes, but they suffer from severe performance degradation when tested on unseen scenes.
Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation
Existing methods usually generate pseudo labels from class activation map (CAM) and then train a segmentation model.
Embracing Single Stride 3D Object Detector with Sparse Transformer
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases.
Ranked #3 on
3D Object Detection
on waymo cyclist
Immortal Tracker: Tracklet Never Dies
We employ a simple Kalman filter for trajectory prediction and preserve the tracklet by prediction when the target is not visible.
OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION
In this paper, we work on object dynamics and propose Object Dynamics Distillation Network (ODDN), a framework that distillates explicit object dynamics (e. g., velocity) from sequential static representations.
A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation
Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property protection.
GAIA: A Transfer Learning System of Object Detection that Fits Your Needs
Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently.
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.
Ranked #4 on
Image Inpainting
on CelebA-HQ
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy
A practical long-term tracker typically contains three key properties, i. e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism.
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.
Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory.
Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions.
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
Then the association problem turns into a general graph matching between tracklet graph and detection graph.
RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection
The most notable difference with previous works is that our method is purely based on the range view representation.
RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection
We first analyze the existing range-view-based methods and find two issues overlooked by previous works: 1) the scale variation between nearby and far away objects; 2) the inconsistency between the 2D range image coordinates used in feature extraction and the 3D Cartesian coordinates used in output.
Uncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation
Unsupervised domain adaptation for semantic segmentation aims to assign the pixel-level labels for unlabeled target domain by transferring knowledge from the labeled source domain.
Clothing Status Awareness for Long-Term Person Re-Identification
This work argues that these approaches in fact are not aware of clothing status (i. e., change or no-change) of a pedestrian.
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths, which can be used for training more accurate segmentation models.
Ranked #38 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Unsupervised Object Detection with LiDAR Clues
We further identify another major issue, seldom noticed by the community, that the long-tailed and open-ended (sub-)category distribution should be accommodated.
Manual-Label Free 3D Detection via An Open-Source Simulator
In this paper, we propose a manual-label free 3D detection algorithm that leverages the CARLA simulator to generate a large amount of self-labeled training samples and introduces a novel Domain Adaptive VoxelNet (DA-VoxelNet) that can cross the distribution gap from the synthetic data to the real scenario.
Multi-task Layout Analysis for Historical Handwritten Documents Using Fully Convolutional Networks
Layout analysis is a fundamental process in document image analysis and understanding.
GIFT: A Real-time and Scalable 3D Shape Search Engine
We name the proposed 3D shape search engine, which combines GPU acceleration and Inverted File Twice, as GIFT.
