A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
ESE-FN improves elderly activity recognition accuracy.
Framework for handling long-tailed multi-modal data.
Deep Triplet Networks improve brain imaging modality recognition with limited data.
New model recognizes emotions with missing modalities, improving accuracy.
In emotion recognition, it is difficult to recognize human's emotional states using just a single modality. Besides, the annotation of physiological emotional data is particularly expensive. These two aspects make the building of effective emotion recognition model challenging. In this paper, we first build a multi-vie…
Enhances speech emotion recognition by integrating visual data with attention mechanisms.
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
We propose a novel method, Modality-based Redundancy Reduction Fusion (MRRF), for understanding and modulating the relative contribution of each modality in multimodal inference tasks. This is achieved by obtaining an -way tensor to consider the high-order relationships between modalities and the output laye…
Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy that goes beyond simple feature concatenation and learns to automatically align…
MEx dataset benchmarks HAR and multi-modal fusion for exercise quality.
Improved multi-modal emotion recognition using deep learning.
Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propo…
New deep fusion methods improve human action recognition using depth and inertial sensor data.
Assistive robots can potentially improve the quality of life and personal independence of elderly people by supporting everyday life activities. To guarantee a safe and intuitive interaction between human and robot, human intentions need to be recognized automatically. As humans communicate their intentions multimodall…
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the r…
In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels. The proposed approach employs a pre-trained convolution neural network and transfer learning to extract features from video …
Paper presents an audiovisual model to recognize sounds from weakly labeled video data.
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life such as behavior and context. The automatic and unobtrusive sensing of behavioral context can help develop solutions for assisted living, fit…
Paper presents a CNN-RNN method for multi-dimensional emotion recognition in-the-wild.
New approach improves human activity recognition with wearables.
Model improves emotion recognition using multiple physiological signals.
Dictionary learning algorithms have been successfully used for both reconstructive and discriminative tasks, where an input signal is represented with a sparse linear combination of dictionary atoms. While these methods are mostly developed for single-modality scenarios, recent studies have demonstrated the advantages …
This work learns shared word embeddings for acoustic and phonetic sequences.
FineHand learns hand shapes for better ASL recognition.
Unified architecture for multi-modal multi-task learning using transformer.
Improved animated faces using audiovisual and modality dropout.
Technological development aims to produce generations of increasingly efficient robots able to perform complex tasks. This requires considerable efforts, from the scientific community, to find new algorithms that solve computer vision problems, such as object recognition. The diffusion of RGB-D cameras directed the stu…
Study develops sign recognition system for DHH users.
Neural approach enhances AI trustworthiness, generalization, and robustness.
There is a widely-accepted need to revise current forms of health-care provision, with particular interest in sensing systems in the home. Given a multiple-modality sensor platform with heterogeneous network connectivity, as is under development in the Sensor Platform for HEalthcare in Residential Environment (SPHERE) …
Radio frequency (RF) sensors are used alongside other sensing modalities to provide rich representations of the world. Given the high variability of complex-valued target responses, RF systems are susceptible to attacks masking true target characteristics from accurate identification. In this work, we evaluate differen…
Enhances mobile context prediction using weakly supervised learning.
AI misidentifies facial expressions in videos, often misinterpreting happiness as sadness.
Self-attention model improves HAR from wearable sensors.
There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these c…
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and meaningful feature representation of sensor data that does not rely on prior expert know…
Study shows stress affects emotion recognition models, improving generalizability.
Enhances privacy in multimodal emotion recognition models.
New unsupervised learning framework for sound recognition.
Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN…
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The proposed method, termed as Density Aware Metric Learning, enforces the model to le…
This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our method extends the BERT model for text sequences to the case of sequences of rea…
With the rapid development of social media sharing, people often need to manage the growing volume of multimedia data such as large scale video classification and annotation, especially to organize those videos containing human activities. Recently, manifold regularized semi-supervised learning (SSL), which explores th…
AI enhances pollen recognition in veterinary imaging using holographic microscopy.
Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable self-attention layers, and the Memory Fusion Network with attention across modalit…
Automatic emotion recognition (AER) is a challenging task due to the abstract concept and multiple expressions of emotion. Although there is no consensus on a definition, human emotional states usually can be apperceived by auditory and visual systems. Inspired by this cognitive process in human beings, it's natural to…
Study improves pollen detection in optical and holographic images using deep learning.