Discover new research papers
Find recent papers across active research areas, then open the app to turn broad discovery into a personalized research feed shaped by the topics, authors, and sources you follow.
Live paper feed
Scan titles, sources, authors, and short summaries before turning broad discovery into a personalized feed.
The novel paradigm of Generative user interfaces introduces a shift from predefined, static interfaces toward dynamically generated and contextually adaptive user experiences. While personalization in Information Systems (IS) is well established, it has large...
Contemporary distributed teams operate across linguistic and geographic boundaries, creating a persistent demand for communication platforms that transcend language barriers without compromising real-time interaction quality.This paper presents SmartCollab, a...
Massively multiplayer online games (MMOGs) increasingly depend on team collaboration and social interaction, yet most heuristic evaluation of playability (HEP) methods focus on individual player experience and overlook team processes. This study proposes HETP...
A systematic and formal approach to analyse and assess the similarity between several interactive systems, focusing on their behaviours is proposed, which is applied to two similar critical command and control interactive systems for flight safety operations...
A novel automated approach that uses limited application context and screen recordings of user interactions as input to an MLLM that automatically identifies and describes usability issues based on Nielsens usability heuristics, and provides corresponding exp...
This paper presents a comparative analysis of user interface (UI) quality in mobile applications offered by the four leading telecommunication operators in Poland: Orange, Play, Plus, and T-Mobile. The study aims to evaluate the quality of user interfaces in...
While the field of Human Activity Recognition (HAR) continues to draw interest from researchers and advance in important ways, some key challenges remain. One of the most difficult aspects of building HAR models that show good performance in real-world settin...
A human fall image recognition method that integrates YOLOv8 and Transformer is proposed, and multi-scale feature fusion is achieved through a feature pyramid network, thereby enhancing the detection accuracy for fall targets of varying scales.
ComODO is a cross-modal self-supervised distillation framework that transfers semantic knowledge from video to IMU without requiring labels, and is compatible with diverse pretrained video and time-series models, offering the potential to leverage more powerf...
This study investigates the efficacy of deep recurrent neural networks, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures, for fall detection utilizing time-series sensor data. The experimental evaluation is conducted on...
DeM-FCN is proposed, a lightweight and purely convolutional framework for smart dumbbell-based resistance-training activity recognition that provides a favorable accuracy-efficiency trade-off for wearable resistance-training recognition and offers a practical...
A deterministic Mixture of Experts (MoE) architecture for in-home ADL recognition, in which each expert is a compact transformer specialized to one room of the home (bedroom, kitchen, bathroom, living area), suggests that room-aware expert specialization may...
Human activity recognition based on wearable sensor data has become increasingly important due to its applications in areas such as healthcare, fitness tracking, and intelligent environments. The widespread use of sensor-equipped devices has led to the genera...
The proposed SFM is low-cost, foldable, portable, and capable of supporting real-time monitoring and proactive safety management in the elderly and contributes to the development of smart home healthcare systems.
WAD-YOLO is proposed, an efficient and lightweight fall detection algorithm tailored for visual sensor systems, based on wavelet transform and dynamic convolution, which is theoretically promising for lightweight, high-accuracy fall detection on edge sensor p...
A comprehensive survey of HAR research from 2004 to February 2026 is presented, systematically organizing the literature according to a canonical processing pipeline that includes sensing modalities/domains, feature representations, temporal modeling strategi...
FAQ
Follow the topics, authors, and sources that define your field in Scollr. New papers in those areas flow into a personalized feed, so finding new research papers becomes a quick daily scan instead of a manual search across journals.
Scollr replaces per-journal email alerts with one personalized research feed. You see recent papers from the areas you follow in a single place, with enough context to decide what to open, so keeping up stays a short habit.
Yes. Follow research topics, individual authors, and sources, and Scollr uses those follows plus your reading behavior to recommend papers and shape what appears in your feed.
Yes. Save any paper to your library, add an optional reason, organize saved papers into collections, and build a literature map from anything you save when you are ready to go deeper.