Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks130 from public data
- Voxel Transformer for 3D Object Detection574
Voxel Transformer is presented, a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds that shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Waymo Open dataset.
- DetCo: Unsupervised Contrastive Learning for Object Detection379
Extensive experiments demonstrate that DetCo not only outperforms recent methods on a series of 2D and 3D instance-level detection tasks, but also competitive on image classification.
- A Survey on Video Diffusion Models318
This article presents a comprehensive review of video diffusion models in the AIGC era, and presents an overview of research on diffusion models in the video domain, categorizing the work into three key areas: video generation, video editing, and other video understanding tasks.
- CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending251
A novel lane-sensitive architecture search framework named CurveLane-NAS to automatically capture both long-ranged coherent and accurate short-range curve information while unifying both architecture search and post-processing on curve lane predictions via point blending.
- 219
- 202
- Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection187
This work presents a flexible and high-performance framework, named Pyramid R-CNN, for two-stage 3D object detection from point clouds, which outperforms the state-of-the-art 3D detection models by a large margin on both the KITTI dataset and the Waymo Open dataset.
- NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning145
Experimental results across various training settings and popular VLN benchmarks show the significant superiority of NavCoT over the direct action prediction variants, and through simple parameter-efficient finetuning, this NavCoT outperforms a recent GPT4-based approach with 7% relative improvement on the R2R dataset.
- 141
- DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment137
An efficient and scalable training framework that incorporates large-scale imagetext pairs to achieve open-vocabulary object detection (OVD) and is trained with a hybrid supervision from detection, grounding and image-text pair data under a unified data formulation.
- Holistic Autonomous Driving Understanding by Bird'View Injected Multi-Modal Large Models128
This work proposes a novel SQL-based method to generate instruction-response pairs automatically, which is inspired by the driving logical progression of humans, and presents BEV-InMLLM, an end-to-end method for efficiently deriving instruction-aware Bird's-Eye-View (BEV) features, language-aligned for large language models.
- 128
- CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data116
This work proposes Contrastive Language-Image-Point Cloud Pretraining (CLIP2) to directly learn the transferable 3D point cloud representation in realistic scenarios with a novel proxy alignment mechanism, and exploits naturally-existed correspondences in 2D and 3D scenarios.
- Driver Anomaly Detection: A Dataset and Contrastive Learning Approach114
This work proposes a contrastive learning approach to learn a metric to differentiate normal driving from anomalous driving and introduces a new video-based benchmark, the Driver Anomaly Detection (DAD) dataset, which contains normal driving videos together with a set of anomalous actions in its training set.
- Segmenting Transparent Objects in the Wild with Transformer109
A novel Transformer-based segmentation pipeline termed Trans2Seg is proposed, which significantly outperforms all the CNN-based methods, showing the proposed algorithm's potential ability to solve transparent object segmentation.
- 107
- ONCE-3DLanes: Building Monocular 3D Lane Detection98
This work presents ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space, and presents an extrinsic-free, anchorfree method, called SALAD, regressing the 3D coordinates of lanes in image view without converting the feature map into the bird's-eye view (BEV).
- TransNAS-Bench-101: Improving transferability and Generalizability of Cross-Task Neural Architecture Search98
This work proposes TransNAS-Bench-101, a benchmark dataset containing network performance across seven tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks, and explores two fundamentally different types of search space: cell-level search space and macro- level search space.
- 91
- Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining91
A novel model named Cross-modal contrAstive Product Transformer for instance-level prodUct REtrieval (CAPTURE) is proposed, that excels in capturing the potential synergy between multi- modal inputs via a hybrid-stream transformer in a self-supervised manner.
- SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection90
This paper presents a two-stage coarse-to-fine searching strategy named Structural- to-Modular NAS (SM-NAS) for searching a GPU-friendly design of both an efficient combination of modules and better modular-level architecture for object detection.
- 89
- 88
- 86
- Effective Sparsification of Neural Networks with Global Sparsity Constraint81
ProbMask is proposed, which solves a natural sparsification formulation under global sparsity constraint and can outperform previous state-of-the-art methods by a significant margin, especially in the high pruning rate situation.
- DetCLIPv3: Towards Versatile Generative Open-Vocabulary Object Detection74
In this pa-per, DetCLIPv3 is introduced, a high-performing detector that excels not only at both open-vocabulary object detection, but also generating hierarchical labels for detected objects.
- 74
- 67
- JGR-P2O: Joint Graph Reasoning Based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image65
A novel pixel-wise prediction-based method for 3D hand pose estimation that achieves new state-of-the-art accuracy while running very efficiently with around a speed of 110fps on a single NVIDIA 1080Ti GPU.
- MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving64
The Multi-instance Siamese Network (MultiSiam) remarkably improves generalization ability and achieves state-of-the-art transfer performance on autonomous driving benchmarks, while existing SSL counterparts like MoCo, MoCo-v2, and BYOL show significant performance drop.
- AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results63
This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.
- Mixed Autoencoder for Self-Supervised Visual Representation Learning62
The proposed Mixed Autoencoder (MixedAE) achieves the state-of-the-art transfer results among masked image modeling (MIM) augmentations on different downstream tasks with significant efficiency and is the very first work to consider mixing for MIM from the perspective of pretext task design.
- 62
- CapDet: Unifying Dense Captioning and Open-World Detection Pretraining52
This paper unify the open-world detection and dense caption tasks into a single yet effective framework by introducing an additional dense captioning head to generate the region-grounded captions and proposes a novel method named CapDet to either predict under a given category list or directly generate the category of predicted bounding boxes.
- Face Recognition via Deep Learning Using Data Augmentation Based on Orthogonal Experiments51
This paper addresses the problem of face recognition using convolutional neural networks for daily attendance taking using data augmentation through geometric transformation, image brightness changes, and the application of different filter operations, and determines the best data Augmentation method based on orthogonal experiments.
- G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation50
This paper proposes a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels to provide the optimal guidance to the student and introduces contrastive distillation to effectively capture the information encoded in the relationship between different feature regions.
- Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism49
Comprehensive experiments show that ROSETTA yields state-of-the-art performance on both task-based and class-based continual object detection.
- Adversarial Robustness for Unsupervised Domain Adaptation47
This work proposes to leverage intermediate representations learned by robust ImageNet models to improve the robustness of UDA models by aligning the features of the UDA model with the robust features learned by ImageNet pre-trained models along with domain adaptation training.
- ConQueR: Query Contrast Voxel-DETR for 3D Object Detection42
This paper proposes a simple yet effective sparse 3D detector, named Query Contrast Voxel-DETR (Con-QueR), to eliminate the challenging false positives, and achieve more accurate and sparser predictions, and closes the gap of sparse and dense 3D detectors.
- AutoBERT-Zero: Evolving BERT Backbone from Scratch42
This work makes the first attempt to automatically discover novel pre-trained language model (PLM) backbone on a flexible search space containing the most fundamental operations from scratch and proposes an Operation-Priority Neural Architecture Search (OP-NAS) algorithm, which optimizes both the search algorithm and evaluation of candidate models.
- 34
- Analysis of ranking data34
A literature review of the models and methods developed for analyzing ranking data and the recent advances of the analysis of ranking data are presented.
- Correctable Landmark Discovery via Large Models for Vision-Language Navigation33
In CONSOLE, VLN is cast as an open-world sequential landmark discovery problem, by introducing a novel correctable landmark discovery scheme based on two large models ChatGPT and CLIP, and a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery.
- Multi-objective Neural Architecture Search via Predictive Network Performance Optimization32
Inspired by the nature of the graph structure of a neural network, BOGCN-NAS is proposed, a NAS algorithm using Bayesian Optimization with Graph Convolutional Network (GCN) predictor to adaptively discover and incorporate nodes structure to approximate the performance of the architecture.
- 31
- Manas: multi-agent neural architecture search30
This work frames NAS as a multi-agent problem where agents control a subset of the network and coordinate to reach optimal architectures, and provides two distinct lightweight implementations, with reduced memory requirements, and performances above those of much more computationally expensive methods.
- DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment28
DiffCloth is introduced, a diffusion-based pipeline for cross-modal garment synthesis and manipulation, which empowers diffusion models with flexible compositionality in the fashion domain by structurally aligning the cross-modal semantics.
- Point2Seq: Detecting 3D Objects as Sequences28
Without bells and whistles, the Point2Seq framework significantly out-performs previous anchor- and center-based 3D object detection frameworks, yielding the new state of the art on the challenging ONCE dataset as well as the Waymo Open Dataset.
- EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation28
This paper has a critical insight that improving the feed-forward network (FFN) in BERT has a higher gain than improving the multi-head attention (MHA) since the computational cost of FFN is 2$\sim$3 times larger than MHA.
- Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN28
This paper presents a novel universal object detector called Universal-RCNN that incorporates graph transfer learning for propagating relevant semantic information across multiple datasets to reach semantic coherency and achieves the state-of-the-art results on multiple object detection benchmarks.
- 27
- Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search27
This work proposes Arch-Graph, a transferable NAS method that predicts task-specific optimal architectures with respect to given task embeddings, and shows its transferability and high sample efficiency across numerous tasks, beating many NAS methods designed for both single-task and multi-task search.
- 27
- 26
- MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation25
MixReorg is proposed, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model’s ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence.
- 24
- 24
- CATCH: Context-Based Meta Reinforcement Learning for Transferrable Architecture Search24
This work proposes CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH, which allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces.
- Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving23
An effective multi-task framework, VE-Prompt, is presented, which introduces visual exemplars via task-specific prompting to guide the model toward learning high-quality task- specific representations and bridges transformer-based encoders and convolutional layers for efficient and accurate unified perception in autonomous driving.
- FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration21
A novel yet simple multi-level gradient calibration learning framework across tasks and modalities during optimization, ensuring the downstream tasks pay balanced attention to different modalities.
- 19
- 19
- 18
- 18
- 18
- 18
- 17
- 16
- 16
- 15
- ElixirNet: Relation-Aware Network Architecture Adaptation for Medical Lesion Detection15
A novel ElixirNet that includes three components, TruncatedRPN balances positive and negative data for false positive reduction, Auto-lesion Block is automatically customized for medical images to incorporates relation-aware operations among region proposals, and leads to more suitable and efficient classification and localization.
- 14
- Efficient Sample-based Neural Architecture Search with Learnable Predictor14
BONAS (Bayesian Optimized Neural Architecture Search), a sample-based NAS framework combined with Bayesian Optimization, which applies Evolution Algorithm method as a sampler and Graph Convolutional Network predictor as a surrogate model to adaptively discover and incorporate nodes structure to approximate the performance of the architecture.
- 13
- 13
- 13
- 12
- 11
- 11
- DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability11
This paper proposes DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process, and proposes a novel dual-stream network architecture, which fuses the noisy text embedding with the knowledge of latent images from different scales for image-text discrim inative learning.
- 11
- 11
- 11
- Unseen From Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation10
A Rewriting-driven AugMentation (RAM) paradigm for VLN is proposed, which directly creates the unseen observation-instruction pairs via rewriting human-annotated training data and develops a mixing-then-focusing training strategy with a random observation cropping scheme, effectively enhancing data distribution diversity while suppressing augmentation data noise during training.
- 10
- NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models10
A joint Neural Architecture Search and Online Adaption framework named NASOA is proposed towards a faster task-oriented fine-tuning upon the request of users and proposes a novel joint block and macro level search space to enable a flexible and effi-cient search.
- Water quality prediction at large-Scale: Systematic assessment of decomposition-deep learning models9
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- Poisoning the Well: Can We Simultaneously Attack a Group of Learning Agents?4
A constructive training-time attack on a population of learning agents and additionally make the attack agnostic to the population's size, which shows feasibility and efficacy and efficacy, i.e., the attack is size-agnostic and transferable.
- GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training4
GrowCLIP is proposed, a data-driven automatic model growing algorithm for contrastive language-image pre-training with continuous image-text pairs as input that adopts a dynamic growth space and seeks out the optimal architecture at each growth step to adapt to online learning scenarios.
- 4
- 4
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.