Sorry, you need to enable JavaScript to visit this website.

Due to the noise and low spatial resolution in automotive radar data, exploring temporal relations of learnable features over consecutive 2 radar frames has shown performance gain on downstream tasks (e.g., object detection and tracking) in our previous study. In this paper, we further enhance radar perception by significantly extending the time horizon of temporal relations.

Energy consumption from the selection, training, and deployment of deep learning models has seen a significant uptick recently. This work aims to facilitate the design of energy-efficient deep learning models that require less computational resources and prioritize environmental sustainability by focusing on the energy consumption. Neural architecture search (NAS) benefits from tabular benchmarks, which evaluate NAS strategies cost-effectively through precomputed performance statistics. We advocate for including energy efficiency as an additional performance criterion in NAS.

Abstractive summarization models learned with maximum likelihood estimation (MLE) have been proven to produce hallucinatory content, which heavily limits their real-world
applicability. Preceding studies attribute this problem to the semantic insensitivity of MLE, and they compensate for it with additional unsupervised learning objectives that maximize the metrics of document-summary inferring, however, resulting in unstable and expensive model training. In this paper, we propose a novel supportive windows indexing

Abstractive summarization suffers from exposure bias caused by the teacher-forced maximum likelihood estimation (MLE) learning, that an autoregressive language model predicts the next token distribution conditioned on the exact pre-context during training while on its own predictions at inference. Preceding resolutions for this problem straightforwardly augment the pure token-level MLE with summary-level objectives.

Acoustic-scene-related parameters such as relative transfer functions (RTFs) and power spectral densities (PSDs) of the target source, late reverberation and ambient noise are essential and challenging to estimate. Existing methods typically only estimate a subset of the parameters by assuming the other parameters are known. This can lead to unmatched scenarios and reduced estimation performance. Moreover, many methods process time frames independently, despite they share common information such as the same RTF.

Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST, enhancing coherence and overcoming memory constraints of extended audio segments. Additionally, we propose context dropout to ensure robustness to the absence of context, and further improve performance by adding speaker information. Our proposed contextual E2E-ST outperforms the isolated utterance-based E2E-ST approach.

Network pruning is an effective technique to reduce computation costs for deep model deployment on resource-constraint devices. Searching superior sub-networks from a vast search space through Neural Architecture Search (NAS) , which conducts a one-shot supernet used as a performance estimator, is still time-consuming. In addition to searching ineffciency, such solutions also focus on FLOPs budget and suffer from an inferior ranking consistency between supernet-inherited and stand-alone performance. To solve the problems above, we propose a framework, namely DBS.

Modern social media platforms play an important role in facilitating rapid dissemination of information through their massive user networks. Fake news, misinformation, and unverifiable facts on social media platforms propagate disharmony and affect society. In this paper, we consider the problem of misinformation detection which classify news items as fake or real. Specifically, driven by experiential studies on real-world social media platforms, we propose a probabilistic Markovian information spread model over networks modeled by graphs.

Accurate and automated gland segmentation on pathological images can assist pathologists in diagnosing the malignancy of colorectal adenocarcinoma. However, due to various gland shapes, severe deformation of malignant glands, and overlapping adhesions between glands. Gland segmentation has always been very challenging. To address these problems, we propose a DEA model. This model consists of two branches: the backbone encoding and decoding network and the local semantic extraction network.

Visual Word Sense Disambiguation (Visual-WSD), as a subtask of fine-grained image-text retrieval, requires a high level of language-vision understanding to capture and exploit the nuanced relationships between text and visual features. However, the cross-linguistic background only with limited contextual information is considered the most significant challenges for this task.