相关论文: Sketchformer: Transformer-based Representation for…

In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoFormer seamlessly integrates prototype learning with Transformer…

The recent rise of generative artificial intelligence (AI), powered by Transformer networks, has achieved remarkable success in natural language processing, computer vision, and graphics. However, the application of Transformers in…

Transformer architectures achieve state-of-the-art performance across a wide range of pattern recognition and natural language processing tasks, but their scaling is accompanied by substantial parameter growth and redundancy in the…

The objective of this paper is to design an embedding method that maps local features describing an image (e.g. SIFT) to a higher dimensional representation useful for the image retrieval problem. First, motivated by the relationship…

Sketching provides an intuitive way to convey dynamic intent in animation authoring (i.e., how elements change over time and space), making it a natural medium for automatic content creation. Yet existing approaches often constrain sketches…

This paper proposes a novel approach to word embeddings in Transformer models by utilizing spinors from geometric algebra. Spinors offer a rich mathematical framework capable of capturing complex relationships and transformations in…

Source code representations are key in applying machine learning techniques for processing and analyzing programs. A popular approach in representing source code is neural source code embeddings that represents programs with…

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework.…

We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables…

Learning to fuse vision and language information and representing them is an important research problem with many applications. Recent progresses have leveraged the ideas of pre-training (from language modeling) and attention layers in…

Drawing freehand sketches of mechanical components on multimedia devices for AI-based engineering modeling has become a new trend. However, its development is being impeded because existing works cannot produce suitable sketches for…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Sign language recognition from sequences of monocular images or 2D poses is a challenging field, not only due to the difficulty to infer 3D information from 2D data, but also due to the temporal relationship between the sequences of…

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger…

In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities…

Traffic forecasting is a cornerstone of smart city management, enabling efficient resource allocation and transportation planning. Deep learning, with its ability to capture complex nonlinear patterns in spatiotemporal (ST) data, has…

Surface material recognition is a key component in robotic perception and physical interaction, particularly when leveraging both tactile and visual sensory inputs. In this work, we propose Surformer v1, a transformer-based architecture…

We present a generative model which can automatically summarize the stroke composition of free-hand sketches of a given category. When our model is fit to a collection of sketches with similar poses, it discovers and learns the structure…

Deep learning applied to the reconstruction of 3D shapes has seen growing interest. A popular approach to 3D reconstruction and generation in recent years has been the CNN encoder-decoder model usually applied in voxel space. However, this…

Spiking neural networks (SNNs) have made great progress on both performance and efficiency over the last few years,but their unique working pattern makes it hard to train a high-performance low-latency SNN.Thus the development of SNNs still…