Related papers: Video Stream Retrieval of Unseen Queries using Sem…
This paper presents a novel approach for temporal and semantic segmentation of edited videos into meaningful segments, from the point of view of the storytelling structure. The objective is to decompose a long video into more manageable…
Among the vast information available on the web, social media streams capture what people currently pay attention to and how they feel about certain topics. Awareness of such trending topics plays a crucial role in multimedia systems such…
We present a novel framework for finding complex activities matching user-described queries in cluttered surveillance videos. The wide diversity of queries coupled with unavailability of annotated activity data limits our ability to train…
In this work, we pioneer Semantic Flow, a neural semantic representation of dynamic scenes from monocular videos. In contrast to previous NeRF methods that reconstruct dynamic scenes from the colors and volume densities of individual…
This paper presents a video summarization technique for an Internet video to provide a quick way to overview its content. This is a challenging problem because finding important or informative parts of the original video requires to…
Motivated by the increasing need of saving search effort by obtaining relevant video clips instead of whole videos, we propose a new task, named Semantic Video Moments Retrieval at scale (SVMR), which aims at finding relevant videos coupled…
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…
This work is devoted to a certain class of probabilistic snapshots for elements of the observed data stream. We show you how one can control their probabilistic properties and we show some potential applications. Our solution can be used to…
Given a stream of entries over time in a multi-dimensional data setting where concept drift is present, how can we detect anomalous activities? Most of the existing unsupervised anomaly detection approaches seek to detect anomalous events…
The rapid growth of video on the internet has made searching for video content using natural language queries a significant challenge. Human-generated queries for video datasets `in the wild' vary a lot in terms of degree of specificity,…
As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…
Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and…
Streamlining content discovery within media archives requires integrating advanced data representations and effective visualization techniques for clear communication of video topics to users. The proposed system addresses the challenge of…
Much of the delivery of University education is now by synchronous or asynchronous video. For students, one of the challenges is managing the sheer volume of such video material as video presentations of taught material are difficult to…
Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple finding: a sliding-window baseline that feeds only the most recent N frames to…
Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years. Despite recent progress, imperfect annotations in existing video retrieval datasets have…
Interactive video retrieval is a cooperative process between humans and retrieval systems. Large-scale evaluation campaigns, however, often overlook human factors, such as the effects of perception, attention, and memory, when assessing…
The aim of process discovery, originating from the area of process mining, is to discover a process model based on business process execution data. A majority of process discovery techniques relies on an event log as an input. An event log…
Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, such as fixed memory compression or reliance on a single model, forcing a trade-off: fast…
Although the problem of automatic video summarization has recently received a lot of attention, the problem of creating a video summary that also highlights elements relevant to a search query has been less studied. We address this problem…