Estimating global human motion from moving cameras is challenging due to the entanglement of human and camera motions. To mitigate the ambiguity, existing methods leverage learned human motion priors, which however often result in oversmoothed motions with misaligned 2D projections. To tackle this problem, we propose COIN, a control-inpainting motion diffusion prior that enables fine-grained control to disentangle human and camera motions. Although pre-trained motion diffusion models encode rich motion priors, we find it non-trivial to leverage such knowledge to guide global motion estimation from RGB videos. COIN introduces a novel control-inpainting score distillation sampling method to ensure well-aligned, consistent, and high-quality motion from the diffusion prior within a joint optimization framework. Furthermore, we introduce a new human-scene relation loss to alleviate the scale ambiguity by enforcing consistency among the humans, camera, and scene. Experiments on three challenging benchmarks demonstrate the effectiveness of COIN, which outperforms the state-of-the-art methods in terms of global human motion estimation and camera motion estimation. As an illustrative example, COIN outperforms the state-of-the-art method by 33% in world joint position error (W-MPJPE) on the RICH dataset.

This paper examines the influence of recommender systems on local music representation, discussing prior findings from an empirical study on the LFM-2b public dataset. This prior study argued that different recommender systems exhibit algorithmic biases shifting music consumption either towards or against local content. However, LFM-2b users do not reflect the diverse audience of music streaming services. To assess the robustness of this study's conclusions, we conduct a comparative analysis using proprietary listening data from a global music streaming service, which we publicly release alongside this paper. We observe significant differences in local music consumption patterns between our dataset and LFM-2b, suggesting that caution should be exercised when drawing conclusions on local music based solely on LFM-2b. Moreover, we show that the algorithmic biases exhibited in the original work vary in our dataset, and that several unexplored model parameters can significantly influence these biases and affect the study's conclusion on both datasets. Finally, we discuss the complexity of accurately labeling local music, emphasizing the risk of misleading conclusions due to unreliable, biased, or incomplete labels. To encourage further research and ensure reproducibility, we have publicly shared our dataset and code.

Point-source transient events (PSTEs) - optical events that are both extremely fast and extremely small - pose several challenges to an imaging system. Due to their speed, accurately characterizing such events often requires detectors with very high frame rates. Due to their size, accurately detecting such events requires maintaining coverage over an extended field-of-view, often through the use of imaging focal plane arrays (FPA) with a global shutter readout. Traditional imaging systems that meet these requirements are costly in terms of price, size, weight, power consumption, and data bandwidth, and there is a need for cheaper solutions with adequate temporal and spatial coverage. To address these issues, we develop a novel compressed sensing algorithm adapted to the rolling shutter readout of an imaging system. This approach enables reconstruction of a PSTE signature at the sampling rate of the rolling shutter, offering a 1-2 order of magnitude temporal speedup and a proportional reduction in data bandwidth. We present empirical results demonstrating accurate recovery of PSTEs using measurements that are spatially undersampled by a factor of 25, and our simulations show that, relative to other compressed sensing algorithms, our algorithm is both faster and yields higher quality reconstructions. We also present theoretical results characterizing our algorithm and corroborating simulations. The potential impact of our work includes the development of much faster, cheaper sensor solutions for PSTE detection and characterization.

Fox News chief political anchor Bret Baier has the latest on the pros and cons of the bombshell developments on'Special Report.' Elon Musk, co-founder of Tesla and SpaceX and owner of X Holdings Corp., speaks at the Milken Institute's Global Conference at the Beverly Hilton Hotel,on May 6, 2024, in Beverly Hills, California. 'TOUGH CALL': Tech billionaire Elon Musk has said that California should pass a controversial bill that would regulate artificial intelligence through having tech companies and AI developers be responsible for safety testing and implementing safeguards against cyberattacks. 'NEVER TIRED': While many musicians and celebrities have spoken out against A.I., rapper wiil.i.am is getting in on the technology, announcing a new artificial intelligence app called Raidio.FYI. AI HANDY HELPER: Meta's artificial intelligence chatbot, powered by Llama 3, is designed to make your online experience smoother and more enjoyable across platforms like Facebook, Messenger, Instagram and WhatsApp.

Tech expert Kurt Knutsson reveals how Figure's robot shows advanced manufacturing skills at BMW plant. HP is a household name when it comes to printers, but the company employs questionable practices to maximize profits. Much like Apple, HP aims to create a closed ecosystem, forcing you to use only its ink with its printers, especially if you opt into HP . Recently, I was at my in-laws' home and signed up for HP for them through the app only to discover that once you accept, the printer firmware is updated permanently. There's no way to undo it, and you're locked into using HP ink cartridges to print anything.

Windows PCs are incredibly powerful and flexible, and that's true even before you install any apps. As it turns out, Windows itself is chock-full of useful features that few people actually know about. If you're a college student who wants to take your college laptop to the next level, here are several obscure Windows features that'll help you whether you're taking notes, researching projects, or otherwise. Windows 11 has a feature called Live Captions that listens to audio and automatically generates readable captions on the fly. It works when you're watching a video, but it also works with audio captured by your microphone.

Before bashing out emails and text messages by thumb became an accepted form of communication, typing was a fully manual skill. In the 80s, "the office" was an exclusive preserve for freaks who could type 40 words per minute at least. Those too modest or miserly to sign up for brick-and-mortar classes could pick up a software program called Mavis Beacon Teaches Typing for 50. At my Catholic high school, the application was the typing class. The priests just switched on the computers.

Abstract--We present a novel approach to the 3D sound source localization task for distributed ad-hoc microphone arrays by formulating it as a set-to-set regression problem. By training a multi-modal masked autoencoder model that operates on audio recordings and microphone coordinates, we show that such a formulation allows for accurate localization of the sound source, by reconstructing coordinates masked in the input. Our approach is flexible in the sense that a single model can be used with an arbitrary number of microphones, even when a subset of audio recordings and microphone coordinates are missing. We test our method on simulated and real-world recordings of music and speech in indoor environments, and demonstrate competitive performance compared to both classical and other learning based localization methods. Here, predictions on the music3 recording from the Mapping, positioning and localization are key enabling LuViRa dataset [6] are shown (viewed from above), where a technologies for a wide range of applications.

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods which add new capabilities to the models they are used on. The first adds a recurrence mechanism, which removes the fixed-window sized constraint and improves the efficiency of a transformer decoder. The second allows masked language models (MLMs) to be used for initialization of both the encoder and decoder of a non-autoregressive sequence-to-sequence transformer, opening up generative applications of models which were previously only used for natural language understanding tasks. We also introduce two new techniques for improving the quality of predictions of any transformer decoder without additional finetuning. One, hidden state optimization, can be applied to any transformer decoder to improve the quality of predictions at inference time, especially for few-shot classification. The other, conditional beam search, allows practitioners to search for natural language generation (NLG) model outputs with high likelihood while conditioning on the event that the output is not degenerate (e.g. empty, repetitive, etc.). Finally, we provide theoretical and empirical insights on the divergence of model-likelihood and output quality which has widely been observed in prior work. These insights apply to any model which represents a distribution over text, and apply to language models which are not transformers or even autoregressive. We argue that the NLP community has, to some extent, misunderstood the implications of these findings, and encourage a point of view which has more nuance.

The remarkable success of large language models (LLMs) across various multi-modality applications is well established. However, integrating large language models with humans, or brain dynamics, remains relatively unexplored. In this paper, we introduce BELT-2, a pioneering multi-task model designed to enhance both encoding and decoding performance from EEG signals. To bolster the quality of the EEG encoder, BELT-2 is the first work to innovatively 1) adopt byte-pair encoding (BPE)-level EEG-language alignment and 2) integrate multi-task training and decoding in the EEG domain. Inspired by the idea of \textbf{\textit{Bridging the Brain with GPT}}, we further connect the multi-task EEG encoder with LLMs by utilizing prefix-tuning on intermediary output from the EEG encoder. These innovative efforts make BELT-2 a pioneering breakthrough, making it the first work in the field capable of decoding coherent and readable sentences from non-invasive brain signals. Our experiments highlight significant advancements over prior techniques in both quantitative and qualitative measures, achieving a decoding performance with a BLEU-1 score of 52.2\% on the ZuCo dataset. Furthermore, BELT-2 shows a remarkable improvement ranging from 31\% to 162\% on other translation benchmarks. Codes can be accessed via the provided anonymous link~\footnote{https://anonymous.4open.science/r/BELT-2-0048}.