相关论文: BEAST: Online Joint Beat and Downbeat Tracking Bas…

Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale benchmark for Environmental Sound Deepfake Detection (ESDD). We propose…

Evaluating lesion progression and treatment response via longitudinal lesion tracking plays a critical role in clinical practice. Automated approaches for this task are motivated by prohibitive labor costs and time consumption when lesion…

Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory…

The human ability to track musical downbeats is robust to changes in tempo, and it extends to tempi never previously encountered. We propose a deterministic time-warping operation that enables this skill in a convolutional neural network…

Synthesizing high-quality dynamic medical videos remains a significant challenge due to the need for modeling both spatial consistency and temporal dynamics. Existing Transformer-based approaches face critical limitations, including…

Tracking using bio-inspired event cameras has drawn more and more attention in recent years. Existing works either utilize aligned RGB and event data for accurate tracking or directly learn an event-based tracker. The first category needs…

We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment. Specifically, we construct a 'coreset' representation of streaming data using a…

Recognizing the surrounding environment at low latency is critical in autonomous driving. In real-time environment, surrounding environment changes when processing is over. Current detection models are incapable of dealing with changes in…

The BeEST experiment is a precision laboratory search for physics beyond the standard model that measures the electron capture decay of $^7$Be implanted into superconducting tunnel junction (STJ) detectors. For Phase-III of the experiment,…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

In today's digital landscape, video content dominates internet traffic, underscoring the need for efficient video processing to support seamless live streaming experiences on platforms like YouTube Live, Twitch, and Facebook Live. This…

Multi-object tracking (MOT) is the problem of tracking the state of an unknown and time-varying number of objects using noisy measurements, with important applications such as autonomous driving, tracking animal behavior, defense systems,…

Transformers have become a predominant machine learning workload, they are not only the de-facto standard for natural language processing tasks, but they are also being deployed in other domains such as vision and speech recognition. Many…

After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.…

In this paper, a streaming transmission setup is considered where an encoder observes a new message in the beginning of each block and a decoder sequentially decodes each message after a delay of $T$ blocks. In this streaming setup, the…

HTTP video streaming is in wide use to deliver video over the Internet. With HTTP adaptive steaming, a video playback dynamically selects a video stream from a pre-encoded representation based on available bandwidth and viewport (screen)…

The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…