Related papers: Refining StreamBED Through Expert Interviews, Desi…
Live streaming platforms require real-time monitoring and reaction to social signals, utilizing partial and asynchronous evidence from video, text, and audio. We propose StreamSense, a streaming detector that couples a lightweight streaming…
Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…
Accurately estimating humans' subjective feedback on video fluency, e.g., motion consistency and frame continuity, is crucial for various applications like streaming and gaming. Yet, it has long been overlooked, as prior arts have focused…
In contemporary training for industrial manufacturing, reconciling theoretical knowledge with practical experience continues to be a significant difficulty. As companies transition to more intricate and technology-oriented settings,…
Recent advances in Large Multi-modal Models (LMMs) are primarily focused on offline video understanding. Instead, streaming video understanding poses great challenges to recent models due to its time-sensitive, omni-modal and interactive…
VTubing, the practice of live streaming using virtual avatars, has gained worldwide popularity among streamers seeking to maintain anonymity. While previous research has primarily focused on the social and cultural aspects of VTubing, there…
Virtual reality (VR) has re-emerged as a low-cost, highly accessible consumer product, and training on simulators is rapidly becoming standard in many industrial sectors. However, the available systems are either focusing on gaming context,…
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling. This poses great challenges given the high correlation between…
The rapid advancement of generative AI has made it increasingly challenging to distinguish between deepfake audio and authentic human speech. To overcome the limitations of passive detection methods, we propose StreamMark, a novel deep…
We present ReViVD, a tool for exploring and filtering large trajectory-based datasets using virtual reality. ReViVD's novelty lies in using simple 3D shapes -- such as cuboids, spheres and cylinders -- as queries for users to select and…
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train…
Bird's Eye View (BEV) semantic maps have recently garnered a lot of attention as a useful representation of the environment to tackle assisted and autonomous driving tasks. However, most of the existing work focuses on the fully supervised…
Recent research has shown that language models exploit `artifacts' in benchmarks to solve tasks, rather than truly learning them, leading to inflated model performance. In pursuit of creating better benchmarks, we propose VAIDA, a novel…
Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many…
While training an end-to-end navigation network in the real world is usually of high cost, simulation provides a safe and cheap environment in this training stage. However, training neural network models in simulation brings up the problem…
This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…
Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…
Immersive analytics enables collaborative data analysis in shared virtual spaces. While synchronous collaboration in such environments is well-established, real-world analysis often requires an effective task handover - the transfer of…
Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily.…
Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for…