Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks176 from public data
- InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions1,217
This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs, and reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large- scale parameters from massive datalike ViTs.
- Vision Transformer Adapter for Dense Predictions938
The ViT-Adapter is proposed, which allows plain ViT to achieve comparable performance to vision-specific transformers and facilitate future research and is verified on multiple dense prediction tasks, including object detection, instance segmentation, and semantic segmentation.
- 644
- VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows271
This work proposes a large-scale Visible-Event benchmark (termed VisEvent) and builds a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data.
- DDP: Diffusion Model for Dense Visual Prediction254
The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline and shows attractive properties such as dynamic inference and uncertainty awareness, in contrast to previous single-step discriminative methods.
- Contrastive Boundary Learning for Point Cloud Segmentation202
This paper proposes a novel contrastive boundary learning (CBL) framework for point cloud segmentation that enhances feature discrimination between points across boundaries by contrasting their representations with the assistance of scene contexts at multiple scales.
- Progressive LiDAR adaptation for road detection202
Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes.
- SASA: Semantics-Augmented Set Abstraction for Point-Based 3D Object Detection180
This work proposes a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA), which is an easy-to-plug-in module and able to boost various point-based detectors, including single-stage and two-stage ones, and proposes a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling.
- Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures166
Vision-RWKV (VRWKV), a model adapted from the RWKV model used in the NLP field with necessary modifications for vision tasks, surpasses ViT's performance in image classification and has significantly faster speeds and lower memory usage processing high-resolution inputs.
- Pedestrian attribute recognition: A survey163
The background of pedestrian attribute recognition (PAR), including the fundamental concepts of pedestrian attributes and corresponding challenges are introduced, and existing benchmarks, including popular datasets and evaluation criterion are introduced.
- RBNet: A Deep Neural Network for Unified Road and Road Boundary Detection155
A deep neural network that can detect both road and road boundary in a single process is introduced, called Road and road Boundary detection Network (RBNet), that first investigates the contextual relationship between the road structure and its boundary arrangement and then model them with a Bayesian network.
- TextFuseNet: Scene Text Detection with Richer Fused Features149
The proposed TextFuseNet can learn a more adequate description of arbitrary shapes texts, suppressing false positives and producing more accurate detection results, and can be trained with weak supervision for those datasets that lack character-level annotations.
- MAPF-LNS2: Fast Repairing for Multi-Agent Path Finding via Large Neighborhood Search147
This paper proposes a novel algorithm MAPF-LNS2 based on large neighborhood search for solving multi-Agent Path Finding efficiently that solves 80% of the random-scenario instances with the largest number of agents from the MAPF benchmark suite with a runtime limit of just 5 minutes, which, to the authors' knowledge, has not been achieved by any existing algorithms.
- The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World133
The All-Seeing model (ASM), a unified framework for panoptic visual recognition and understanding, is developed with open-ended language prompts and locations, which allows it to generalize to various vision and language tasks with remarkable zero-shot performance.
- Expression snippet transformer for robust video-based facial expression recognition119
This work designs an attention-augmented snippet feature extractor (AA-SFE) to enhance the encoding of subtle facial movements of each snippet by gradually attending to more salient information, and introduces a shuffled snippet order prediction (SSOP) head and a corresponding loss to improve the modeling of subtle motion changes across subsequent snippets.
- Context Refinement for Object Detection117
A context refinement algorithm that explores rich contextual information to better refine each proposed region and first identifies neighboring regions that may contain useful contexts and then perform refinement based on the extracted and unified contextual information.
- Automatic web spreadsheet data extraction117
A system that automatically extracts relational data from spreadsheets, thereby enabling relational spreadsheet integration and a novel view of how users organize their data in spreadsheets is presented.
- 100
- Towards High Performance Human Keypoint Detection94
This paper develops a hard-negative person detection mining strategy and a joint-training strategy by exploiting abundant unlabeled data that enables CCM to learn discriminative features from massive diverse poses and presents several sub-pixel refinement techniques for postprocessing keypoint predictions to improve detection accuracy.
- A blockchain 3.0 paradigm for digital twins in construction project management89
This paper proposes ChainPM as a Blockchain 3.0 paradigm, which extends Blockchain 2.0 with innovative indexing, query, and smart contracts.
- MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer83
MM-Interleaved is an end-to-end generative model for interleaved image-text data that introduces a multi-scale and multi-image feature synchronizer module, allowing direct access to fine-grained image features in the previous context during the generation process.
- Having the Memory of an Elephant: Long-Term Retrieval and the Use of Analogues in Problem Solving.77
Comparisons of different versions of a target problem indicated that similarity of solution tool affected accessing, mapping, and executing components of problem solving, whereas similarity of goal object had only a moderate effect on accessing.
- A New Chaos-Based Color Image Encryption Scheme with an Efficient Substitution Keystream Generation Strategy66
Experimental results demonstrate that the proposed scheme has a satisfactory level of security and outperforms the conventional schemes in terms of computational efficiency.
- Dynamic Attention Guided Multi-Trajectory Analysis for Single Object Tracking56
This paper proposes to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy that contains multiple target templates, each of which provides its own attention for locating the target in the new frame.
- CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose50
A novel prompt-based Contrastive learning scheme for connecting Language and AniMal Pose (CLAMP) effectively, which enables the first cross-modal animal pose estimation paradigm.
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.