Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks73 from public data
- CCNet: Criss-Cross Attention for Semantic Segmentation3,111
For each pixel, a novel criss-cross attention module in CCNet harvests the contextual information of all the pixels on its criss-cross path by taking a further recurrent operation, each pixel can finally capture the full-image dependencies from all pixels.
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2,221
This work designs a data engine to collect and automatically annotate large-scale unlabeled data and develops an auxiliary supervision to enforce the model to inherit rich semantic priors from pre-trained encoders, which results in a better depth-conditioned ControlNet.
- Executing your Commands via Motion Diffusion in Latent Space766
The proposed Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs and substantially reduce the computational overhead in both the training and inference stages.
- 595
- TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation338
Experimental results demonstrate that the proposed TopFormer method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency.
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos277
Video Depth Anything is proposed for high-quality, consistent depth estimation in super-long videos (over several minutes) without sacrificing efficiency, and sets a new state-of-the-art in zero-shot video depth estimation.
- Devil in the Details: Towards Accurate Single and Multiple Human Parsing268
This paper identifies several useful properties, including feature resolution, global context information and edge details, and performs rigorous analyses to reveal how to leverage them to benefit the human parsing task, resulting in a simple yet effective Context Embedding with Edge Perceiving (CE2P) framework for single human parsing.
- Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis237
This work presents Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns, and proposes an effective model designed for aerial agricultural pattern recognition.
- AlignSeg: Feature-Aligned Segmentation Networks199
This paper proposes Feature-Aligned Segmentation Networks (AlignSeg), a feature aggregation network that adopts a simple learnable interpolation strategy to learn transformation offsets of pixels that can effectively relieve the feature misalignment issue caused by multi-resolution feature aggregation.
- Sa2VA: Marrying SAM2 With MLLM for Dense Grounded Understanding of Images and Videos168
Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications.
- BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs137
BozoGPT is a multi-modal LLM with visual grounding that can perform cross-modAL interaction between vision, audio and language, providing fine-grained understanding of visual objects and other given modalities and performs consistently well when provided by arbitrary modalities.
- SPGNet: Semantic Prediction Guidance for Scene Parsing134
By carefully re-weighting features across stages, a two-stage encoder-decoder network coupled with the proposed Semantic Prediction Guidance (SPG) module can significantly outperform its one-stage counterpart with similar parameters and computations.
- SeaFormer++: Squeeze-Enhanced Axial Transformer for Mobile Visual Recognition132
A new method squeeze-enhanced Axial Transformer (SeaFormer) for mobile visual recognition, designed a generic attention block characterized by the formulation of squeeze Axial and detail enhancement, which can be further used to create a family of backbone architectures with superior cost-effectiveness.
- SeMask: Semantically Masked Transformers for Semantic Segmentation132
This paper argues that incorporating semantic information of the image into pretrained hierarchical transformer-based backbones while finetuning improves the performance considerably and proposes SeMask, a simple and effective framework that incorporates semantic information into the encoder with the help of a semantic attention operation.
- Deep learning-based automated image segmentation for concrete petrographic analysis120
The experimental results showed that CNN outperforms the color-based segmentation by a considerable margin, and has comparable accuracy to human experts, and the segmentation time is reduced to mere seconds.
- 119
- 99
- GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation78
A classification-model-based approach is proposed to investigate the underlying architecture of GPT-4o, where empirical results suggest the model consists of an auto-regressive (AR) combined with a diffusion-based head for image decoding, rather than the VAR-like architectures.
- Deep patch learning for weakly supervised object classification and discovery76
The results show that the proposed weakly supervised patch features via weak supervisions method can obtain state-of-the-art performance on object classification, and very competitive results on object discovery, with faster testing speed than competitors.
- High-Resolution Deep Image Matting64
The proposed HDMatt approach runs matting in a patch-based crop-and-stitch manner for high-resolution inputs with a novel module design to address the contextual dependency and consistency issues between different patches.
- LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models58
This work introduces LOKI, a novel benchmark designed to evaluate the ability of LMMs to detect synthetic data across multiple modalities, and evaluated 22 open-source LMMs and 6 closed-source models on it, highlighting their potential as synthetic data detectors and also revealing some limitations in the development of LMM capabilities.
- 52
- Human De-occlusion: Invisible Perception and Recovery for Humans48
A two-stage framework is proposed to estimate the invisible portions and recover the content inside of human deocclusion and a stacked network structure is devised to refine inaccurate masks from a general instance segmentation model and predict integrated masks simultaneously.
- Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report39
This paper introduces the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly realtime performance on smartphones and IoT platforms.
- The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer34
Sail is introduced, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture that eliminates the need for a separate vision encoder, presenting a more minimalist architecture design.
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 2026-10-14. 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.