Featured

Business

Design

Education

How-to & DIY

Marketing & SEO

Programming

Research

Science

Storyboards

Technology

Semantic Machine Intelligence Lab., Keio Univ.

keio_smilab

0 Stars

Decks

The Confluence of Vision, Language, and Robotics

0

150

[Journal Club] Improving Cross-Modal Retrieval with Set of Diverse Embeddings

0

240

[IROS23]Multimodal Diffusion Segmentation Model for Object Segmentation from Manipulation Instructions

0

120

[IROS23] Prototypical Contrastive Transfer Learning for Multimodal Language Understanding

0

140

how will foundation models change robotics

4

700

[IROS23] Switching Head–Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks

0

310

[RSJ23] Everyday Object Search and Manipulation Based on Target Object Extraction Using Multimodal Foundation Models

0

370

[RSJ23] ENCHANT: Enhanced Nearest-neighbor Captioning with Hypothesis AugmeNTation

1

320

[RSJ23] DialMAT: Dialogue-Enabled Transformer with Moment-Based Adversarial Training

0

750

[RSJ23] Dual ProtoNCE-based Domain Adaptation and Instruction Understanding with Large-Scale Language Models

0

600

[RSJ23]Trimodal Cross-Attentional Transformer for Rearrangement Target Detection Using Visual Foundation Models

0

530

[RSJ23] Referring Expression Segmentation Based on Multimodal Foundation Models and Diffusion Models

0

370

[RSJ23] Learning-To-Rank Approach for Identifying Everyday Objects Using a Physical-World Search Engine

0

340

[Journal club] A Generalization of ViT/MLP-Mixer to Graphs

0

130

[Journal club] VIMA: General Robot Manipulation with Multimodal Prompts

0

93

[Journal Club] Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

0

130

[Journal club] SeqTR: A Simple yet Universal Network for Visual Grounding

0

85

[Journal club] OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses

0

19

Speaker Deck Pro: Add privacy options and schedule the publishing of your decks Upgrade