20 results for “Pyramid Scene Parsing Network”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Introduces U$^2$Mamba, a U-structured network for salient object detection with improved local feature extraction and contextual information.
Shaohui Dai, Yansong Qu, You Shen, Shengchuan Zhang +1 more
The paper introduces PAR3D, a unified part-aware 3D-MLLM framework, to enhance 3D scene understanding by enabling models to reason about and ground both whole objects and their fine-grained parts.
LALE introduces a novel lightweight architecture that efficiently combines local convolutional features and global transformer context for land-cover segmentation, achieving superior efficiency and pe…
Replacing global self-attention in stereo transformers with a data-independent Walsh-Hadamard token mixer reduces compute and latency by a factor of 2.46 and 2.65 respectively.
Xiaoyang Han, Jianhua Li, Kewang Deng, Zukai Chen +13 more
The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…
GraphWrit3R generates a complete scene graph from 3D point cloud or Gaussian Splats inputs without relying on ground-truth object annotations.
Wajeeha Tahir, Anna Tegon, Lionnus Kesting, Gamze İslamoğlu +3 more
This paper introduces Spatial-TRM, a compact recursive model that improves spatial context prediction in natural images.
This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative indu…
Sublinearly structured DNNs achieve feature-learning and prediction consistency comparable to classical models
The paper proposes a method for constructing scene graphs to represent and characterize assembly relationships between components using a Faster R-CNN model, transformer architecture, adjacency matrix…
Maëlic Neau, Salim Baloch, Jakob Suchan, Zoe Falomir +1 more
The paper proposes a model-agnostic framework to improve scene graph generation models under annotation sparsity by capturing visual commonsense knowledge.
The paper proposes BRACS, a training-free steering framework that adaptively corrects visual grounding failures in large vision-language models, significantly reducing object hallucination without sac…
The paper proposes CYKNN, a novel recurrent neural network architecture that directly encodes the CYK parsing algorithm, demonstrating superior performance over large language models on syntactic pars…
The paper proposes AlignG, a method that learns context-conditioned predicate semantics by using prototype feedback to adapt relation representations based on image-specific evidence, significantly im…
This paper proposes PairGS, a framework for open-vocabulary 3D Gaussian segmentation that models pairwise relations between Gaussians using rich signals from 3D Gaussian representations.
Bingyu Li, Da Zhang, Tao Huo, Zhiyuan Zhao +2 more
The paper introduces Multi-temporal Referring Segmentation (MTRS), a new task requiring models to segment language-described temporal changes, and proposes MTRefSeg-R1, a specialized framework that ac…
This paper studies how transformers exploit task-relevant structure in geometrically heterogeneous data and provides a new estimator and generalization bound for in-context learning.
The paper applies network science to demonstrate the feasibility of unsupervised dependency parsing in non-human primates due to their sequence length distribution.
This paper proposes Hierarchical Block-Local Learning (HBLL), a framework for training deep neural networks without full end-to-end backpropagation, achieving $\mathcal{O}(\log N)$ parallel time compl…