Trending Research
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks.
SOTA for Question Answering on SQuAD2.0
LINGUISTIC ACCEPTABILITY NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SEMANTIC TEXTUAL SIMILARITY SENTIMENT ANALYSIS
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
To enable evaluation of progress on code search, we are releasing the CodeSearchNet Corpus and are presenting the CodeSearchNet Challenge, which consists of 99 natural language queries with about 4k expert relevance annotations of likely results from CodeSearchNet Corpus.
Single-Network Whole-Body Pose Estimation
• CMU-Perceptual-Computing-Lab/openpose_train
We present the first single-network approach for 2D~whole-body pose estimation, which entails simultaneous localization of body, face, hands, and feet keypoints.
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• CMU-Perceptual-Computing-Lab/openpose_train
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Unified Language Model Pre-training for Natural Language Understanding and Generation
• microsoft/unilm • 
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
SOTA for Text Summarization on GigaWord (using extra training data)
ABSTRACTIVE TEXT SUMMARIZATION LANGUAGE MODELLING QUESTION ANSWERING QUESTION GENERATION TEXT GENERATION
Towards modular and programmable architecture search
We release an implementation of our language with this paper.
TSM: Temporal Shift Module for Efficient Video Understanding
• MIT-HAN-LAB/temporal-shift-module •
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost.
VIDEO OBJECT DETECTION VIDEO RECOGNITION VIDEO UNDERSTANDING
Non-local Neural Networks
CVPR 2018 • MIT-HAN-LAB/temporal-shift-module •
Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
#3 best model for Instance Segmentation on COCO minival
INSTANCE SEGMENTATION KEYPOINT DETECTION OBJECT DETECTION VIDEO CLASSIFICATION
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
• MIT-HAN-LAB/temporal-shift-module •
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
#3 best model for Multimodal Activity Recognition on EV-Action
ACTION RECOGNITION IN VIDEOS MULTIMODAL ACTIVITY RECOGNITION
Language Models are Unsupervised Multitask Learners
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
SOTA for Language Modelling on Text8 (using extra training data)
COMMON SENSE REASONING DOCUMENT SUMMARIZATION LANGUAGE MODELLING MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION TEXT GENERATION