Latest Research
CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows
Our approach results in a computationally and memory-efficient model: CFLOW-AD is faster and smaller by a factor of 10x than prior state-of-the-art with the same input setting.
Image Scene Graph Generation (SGG) Benchmark
microsoft/scene_graph_benchmark
•
•
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection.
Greedy Gradient Ensemble for Robust Visual Question Answering
Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information.
Ranked #2 on
Visual Question Answering
on VQA-CP
Energy-based Unknown Intent Detection with Data Manipulation
yawenouyang/GOT
•
•
Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set.
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation
bo-miao/MAMP
•
•
Moreover, MAMP performs on par with many supervised video object segmentation methods.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
To make the method more practical, we propose a well-designed enhancer that can process a 4K-resolution image over 200 FPS but surpasses the contemporaneous single style image enhancement methods in terms of PSNR, SSIM, and LPIPS.
CCGL: Contrastive Cascade Graph Learning
Xovee/ccgl
•
•
Second, it learns a generic model for graph cascade tasks via self-supervised contrastive pre-training using both unlabeled and labeled data.
Image-Based Parking Space Occupancy Classification: Dataset and Baseline
martin-marek/parking-space-occupancy
•
•
We introduce a new dataset for image-based parking space occupancy classification: ACPDS.
Structural Learning of Probabilistic Sentential Decision Diagrams under Partial Closed-World Assumption
Probabilistic sentential decision diagrams are a class of structured-decomposable probabilistic circuits especially designed to embed logical constraints.
Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
BME-SmartLab/UTI-to-STFT-Tacotron2
•
•
In this paper, we experimented with transfer learning and adaptation of a Tacotron2 text-to-speech model to improve the final synthesis quality of ultrasound-based articulatory-to-acoustic mapping with a limited database.
