Search Results for author:
Found 13 papers, 6 papers with code
Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models
When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion.
Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations
Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development, while most existing research has primarily centered on single-user chatbots that focus on deciding "What" to answer after user inputs.
BatchPrompt: Accomplish more with less
We have two initial observations for prompting with batched data.
CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials
While designing sustainable and resilient urban built environment is increasingly promoted around the world, significant data gaps have made research on pressing sustainability issues challenging to carry out.
NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences
Visual place recognition (VPR) is critical in not only localization and mapping for autonomous driving vehicles, but also in assistive navigation for the visually impaired population.
IntentVizor: Towards Generic Query Guided Interactive Video Summarization
There is a growing interest in the integration of user queries into video summarization or query-driven video summarization.
Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification
To address such concerns, we have a rethinking of crowdsourcing annotations: Our simple hypothesis is that if the annotators only partially annotate multi-label images with salient labels they are confident in, there will be fewer annotation errors and annotators will spend less time on uncertain labels.
ERA: Entity Relationship Aware Video Summarization with Wasserstein GAN
This type of methods includes a summarizer and a discriminator.
SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images
In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.
Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks
To be more specific, we first learn the prototype representation of each aerial scene from single-scene aerial image datasets and store it in an external memory.
Reciprocal Landmark Detection and Tracking with Extremely Few Annotations
The model is trained using few annotated frames across the entire cardiac cine sequence to generate consistent detection and tracking of landmarks, and an adversarial training for the model is proposed to take advantage of these annotated frames.
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution.
Ranked #1 on
Domain Adaptation
on SYNSIG-to-GTSRB
DT-LET: Deep Transfer Learning by Exploring where to Transfer
Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains.
