Search Results for author:
Found 18 papers, 3 papers with code
DocTr: Document Transformer for Structured Information Extraction in Documents
We present a new formulation for structured information extraction (SIE) from visually rich documents.
Ranked #2 on
Entity Linking
on FUNSD
Modeling Dual Period-Varying Preferences for Takeaway Recommendation
Different from traditional recommendation, takeaway recommendation faces two main challenges: (1) Dual Interaction-Aware Preference Modeling.
rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement
However, they focus on the contrastive learning between samples, which neglect the inherent self-similar prior in physiological signals and seem to have a limited ability to cope with noisy.
PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks.
Ranked #1 on
Referring Expression Segmentation
on ReferIt
(using extra training data)
Light Field Depth Estimation via Stitched Epipolar Plane Images
This strategy involves determining the depth of such regions by progressing from the edges towards the interior, prioritizing accurate regions over coarse regions.
Humble Teachers Teach Better Students for Semi-Supervised Object Detection
We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework.
Dynamically Grown Generative Adversarial Networks
Recent work introduced progressive network growing as a promising way to ease the training for large GANs, but the model design and architecture-growing strategy still remain under-explored and needs manual design for different image data.
Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries
Computer vision applications such as visual relationship detection and human object interaction can be formulated as a composite (structured) set detection problem in which both the parts (subject, object, and predicate) and the sum (triplet as a whole) are to be detected in a hierarchical fashion.
Human-Object Interaction Detection
Relationship Detection
+1
Computational analysis of pathological image enables interpretable prediction for microsatellite instability
Microsatellite instability (MSI) is associated with several tumor types and its status has become increasingly vital in guiding patient treatment decisions.
Visual Question Answering on Image Sets
To enable research in this new topic, we introduce two ISVQA datasets - indoor and outdoor scenes.
Unsupervised Discovery of Object Landmarks as Structural Representations
Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way.
Unsupervised Facial Landmark Detection
Unsupervised Human Pose Estimation
+1
Hierarchical Novelty Detection for Visual Object Recognition
The essential ingredients of our methods are confidence-calibrated classifiers, data relabeling, and the leave-one-out strategy for modeling novel classes under the hierarchical taxonomy.
Towards Understanding the Invertibility of Convolutional Neural Networks
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible.
Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries
Our training objective encourages better localization on single images, incorporates text phrases in a broad range, and properly pairs image regions with text phrases into positive and negative examples.
Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
Inspired by the recent trend toward revisiting the importance of unsupervised learning, we investigate joint supervised and unsupervised learning in a large-scale setting by augmenting existing neural networks with decoding pathways for reconstruction.
Deep Visual Analogy-Making
In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding.
Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
Object detection systems based on the deep convolutional neural network (CNN) have recently made ground- breaking advances on several object detection benchmarks.
Robust Face Recognition by Constrained Part-based Alignment
By assuming a human face as piece-wise planar surfaces, where each surface corresponds to a facial part, we develop in this paper a Constrained Part-based Alignment (CPA) algorithm for face recognition across pose and/or expression.
