My name is Shizhe Chen. I am a postdoctoral researcher at INRIA Paris, working in the WILLOW project-team with Ivan Laptev and Cordelia Schmid. I received my PhD degree from Renmin University of China in 2020, advised by Prof. Qin Jin. During my doctoral studies, I visited Carnegie Mellon University, University of Adelaide, and interned at Microsoft Research Asia. Prior to my PhD, I earned my Bachelor's degree in Computer Science from Renmin University of China in 2015.
My research interests include vision-and-language, action recognition, and more recently, embodied AI.
My CV can be found here.

[Google Scholar] [GitHub] [Linkedin]

gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction

Language Conditioned Spatial Relation Reasoning for 3D Object Grounding

Instruction-driven history-aware policies for robotic manipulations

Learning from Unlabeled 3D Environments for Vision-and-Language Navigation

Few-Shot Action Recognition with Hierarchical Matching and Contrastive Learning

Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation

Vrdformer: End-to-end video visual relation detection with transformers

History Aware Multimodal Transformer for Vision-and-Language Navigation

Elaborative Rehearsal for Zero-shot Action Recognition

Airbert: In-domain Pretraining for Vision-and-Language Navigation

Question-controlled Text-aware Image Captioning

Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training

Sketch, Ground, and Refine: Top-Down Dense Video Captioning

Towards Diverse Paragraph Captioning for Untrimmed Videos

Say as You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs

Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning

Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences

From words to sentence: A progressive learning approach for zero-resource machine translation with visual pivots

Unsupervised Bilingual Lexicon Induction from Mono-lingual Multimodal Data

Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards

Visual Relation Detection with Multi-Level Attention

YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension

Generating Video Descriptions with Latent Topic Guidance

Class-aware Self-attention for Audio Event Recognition

Go to Google Scholar for full publication list