Search Results for author:
Found 11 papers, 3 papers with code
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems.
Ranked #3 on
Data-to-Text Generation
on E2E NLG Challenge
Automated Material Properties Extraction For Enhanced Beauty Product Discovery and Makeup Virtual Try-on
An intelligent approach for product discovery is required to enhance the makeup shopping experience to make it more convenient and satisfying.
Unsupervised Scene Sketch to Photo Synthesis
Taking this advantage, we synthesize a photo-realistic image by combining the structure of a sketch and the visual style of a reference photo.
Structured Graph Variational Autoencoders for Indoor Furniture layout Generation
The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph.
VoiceMoji: A Novel On-Device Pipeline for Seamless Emoji Insertion in Dictation
To the best of our knowledge, this is the first work that shows how to add emoji(s) in the transcribed text.
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects.
LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network
To build high-quality real-world conversational solutions for edge devices, there is a need for deploying intent detection model on device.
Ranked #1 on
Intent Detection
on SNIPS
(model size metric)
RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View
In addition to using learnt robust features, our approach learns an additional ranking function to estimate the final layout instead of using optimization.
Multimodal Shape Completion via IMLE
Shape completion is the problem of completing partial input shapes such as partial scans.
A character representation enhanced on-device Intent Classification
Our experiments prove that our proposed model outperforms existing approaches and achieves state-of-the-art results on benchmark datasets.
Contextual Diversity for Active Learning
Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field.
