A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Efficient model for foggy scene understanding in vehicles.
A neural scene representation framework enforcing 3D transformations.
Topic models (e.g., pLSA, LDA, SLDA) have been widely used for segmenting imagery. These models are confined to crisp segmentation. Yet, there are many images in which some regions cannot be assigned a crisp label (e.g., transition regions between a foggy sky and the ground or between sand and water at a beach). In the…
New model separates objects in scenes, enabling novel arrangements and depth.
Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet …
ROOTS learns to represent and render 3D scenes with object-centric models.
Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose Information Pursuit, a Bayesian framework for scene parsing that combines prior models …
SPACE models complex scenes by decomposing objects and backgrounds.
NeRF-VAE generates 3D scenes with geometric structure from few images.
Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, char…
Improved acoustic scene classification with factorized CNN.
A new method for estimating joint value functions in multi-scene reinforcement learning.
Generative models learn from unlabeled videos via object segmentation and scene modeling.
Generative Multisensory Network learns 3D scene representations from multiple modalities.
Pix2Shape learns 3D scene representations from single images without supervision.
Paper improves reinforcement learning in multi-scene tasks.
RICH models scenes as hierarchical tree to learn and generate complex compositions.
Improves reinforcement learning agent's scene-specific value function.
A novel method for visual question answering using scene graphs and reinforcement learning.
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algor…
Acoustic scene classification is the task of identifying the scene from which the audio signal is recorded. Convolutional neural network (CNN) models are widely adopted with proven successes in acoustic scene classification. However, there is little insight on how an audio scene is perceived in CNN, as what have been d…
Generative model creates realistic scenes from pixel-wise labels.
P3I learns holistic scene representations from a single image.
Generates coherent 3D scenes from monocular videos without supervision.
SCALOR learns scalable object representations for crowded scenes.
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
Proposes Deep Scenes for interaction-aware scene understanding in reinforcement learning for autonomous driving.
Topic models (e.g., pLSA, LDA, sLDA) have been widely used for segmenting imagery. However, these models are confined to crisp segmentation, forcing a visual word (i.e., an image patch) to belong to one and only one topic. Yet, there are many images in which some regions cannot be assigned a crisp categorical label (e.…
Deep network predicts action sequences for complex tasks from a scene image.
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions can simplify reasoning and facilitate imagination of novel scenarios. In particu…
Generative model improves scene graph prediction for rare compositions.
Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in computer vision remain local. Pictorial structures have arisen as a fundamental parts-bas…
ObSuRF converts a single image into a 3D model with NeRFs.
A multi-head attention network improves ASC by recognizing overlapping sound patterns.
We propose a completely unsupervised method to understand audio scenes observed with random microphone arrangements by decomposing the scene into its constituent sources and their relative presence in each microphone. To this end, we formulate a neural network architecture that can be interpreted as a nonnegative tenso…
SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.
Deep learning within the context of point clouds has gained much research interest in recent years mostly due to the promising results that have been achieved on a number of challenging benchmarks, such as 3D shape recognition and scene semantic segmentation. In many realistic settings however, snapshots of the environ…
Recent progress on automatic generation of image captions has shown that it is possible to describe the most salient information conveyed by images with accurate and meaningful sentences. In this paper, we propose an image caption system that exploits the parallel structures between images and sentences. In our model, …
While great progress has been made recently in automatic image manipulation, it has been limited to object centric images like faces or structured scene datasets. In this work, we take a step towards general scene-level image editing by developing an automatic interaction-free object removal model. Our model learns to …
BPI models 2D patterns on multiple planes and 3D scene from a single image.
Constellation learns group-level visual relationships for abstract reasoning.
This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes. To demonstrate its potential, this model is employed to evaluate the performance of a large set of acoustic events detection systems. This model allows us to expli…
Proposes a method to quantify uncertainty in deterministic image classifiers.
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an extreme diversity space, such as \textit{person-behind-person} and \textit{car-behind…
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via co…
Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structu…
The paper proposes a model to forecast traffic motion from sensor data.
Object-centric learning improves generalization and robustness in multi-object scenes.