Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks187 from public data
- Recent advances in convolutional neural networks6,499
This paper details the improvements of CNN on different aspects, including layer design, activation function, loss function, regularization, optimization and fast computation, and introduces various applications of convolutional neural networks in computer vision, speech and natural language processing.
- Deep learning for event-driven stock prediction866
This work proposes a deep learning method for event-driven stock market prediction that can achieve nearly 6% improvements on S&P 500 index prediction and individual stock prediction, respectively, compared to state-of-the-art baseline methods.
- Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation707
For the first time, a bottom-up approach could deliver state-of-the-art results on panoptic segmentation, and performs on par with several top-down approaches on the challenging COCO dataset.
- 554
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network400
This work proposes a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks that attains state-of-the-art results on the THUMOS14 dataset and outstanding performance on ActivityNet1.3 even with its weak supervision.
- A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding299
A novel framework for SLU to better incorporate the intent information, which further guiding the slot filling is proposed, which achieves the state-of-the-art performance and outperforms other previous methods by a large margin.
- Color image encryption by using Arnold transform and color-blend operation in discrete cosine transform domains229
In this encryption scheme the operations mentioned above are performed twice continuously, so the parameters of Arnold transform and the random angle serve as the key of the color image encryption method.
- Remote sensing image fusion via wavelet transform and sparse representation152
The proposed fusion method can well preserve the spectral information and the spatial detail information of the original images, and could well maintain the spectral characteristics of fusion images with a high spatial resolution.
- 145
- 135
- Knowledge-Driven Event Embedding for Stock Prediction130
A joint model to combine knowledge graph information into the objective function of an event embedding learning model is proposed, which is more capable of obtaining better event embeddings and making more accurate prediction on stock market volatilities.
- 126
- Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association111
A novel and efficient way to obtain discriminative appearance-based tracklet affinity models that jointly learns the convolutional neural networks (CNNs) and temporally constrained metrics under a unified framework is proposed.
- GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling107
This paper proposes a non-autoregressive model for joint multiple intent detection and slot filling, achieving more fast and accurate performance while being 11.5 times faster.
- 104
- 100
- Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog99
This work investigates methods that can make explicit use of domain knowledge and introduce a shared-private network to learn shared and specific knowledge and proposes a novel Dynamic Fusion Network (DF-Net) which automatically exploit the relevance between the target domain and each domain.
- Learning Invariant Color Features for Person Reidentification90
This paper proposes an approach for learning color patterns from pixels sampled from images across two camera views using color as the only cue, and compares it with all the photometric invariant color spaces and shows superior performance over all of them.
- Mining User Consumption Intention from Social Media Using Domain Adaptive Convolutional Neural Network89
The results show that CIMM offers a powerful paradigm for effectively identifying users’ consumption intention based on their social media data, and suggest that a great potential for the model to significantly increase effectiveness of product recommendations and targeted advertising.
- 88
- 68
- Segmentation and quantification of blood vessels for OCT-based micro-angiograms using hybrid shape/intensity compounding56
A hybrid Hessian/intensity based method to segment and quantify shape and diameter of the blood vessels innervating capillary beds that are imaged by functional OCT in vivo is proposed and believes that this method will play an important role in the quantification of micro-angiograms for microcirculation research in ophthalmology and diagnosing retinal eye diseases involved with microcirculation.
- Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications55
A review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications is proposed, with the intention of inspiring future research endeavors.
- 49
- 43
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.