Related papers: Interactive Video Corpus Moment Retrieval using Re…
Multimedia information retrieval from videos remains a challenging problem. While recent systems have advanced multimodal search through semantic, object, and OCR queries - and can retrieve temporally consecutive scenes - they often rely on…
Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…
Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training…
This paper presents a novel semi-supervised deep learning algorithm for retrieving similar 2D and 3D videos based on visual content. The proposed approach combines the power of deep convolutional and recurrent neural networks with dynamic…
In this paper, we propose an efficient and high-performance method for partially relevant video retrieval, which aims to retrieve long videos that contain at least one moment relevant to the input text query. The challenge lies in encoding…
Keyframe selection has become essential for video understanding with vision-language models (VLMs) due to limited input tokens and the temporal sparsity of relevant information across video frames. Video understanding often relies on…
We consider text retrieval within dense representational space in real-world settings such as e-commerce search where (a) document popularity and (b) diversity of queries associated with a document have a skewed distribution. Most of the…
Large video-language models (LVLMs) have shown remarkable performance across various video-language tasks. However, they encounter significant challenges when processing long videos because of the large number of video frames involved.…
Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…
Video recommendation has become an essential way of helping people explore the massive videos and discover the ones that may be of interest to them. In the existing video recommender systems, the models make the recommendations based on the…
The paper focuses on the problem of learning saccades enabling visual object search. The developed system combines reinforcement learning with a neural network for learning to predict the possible outcomes of its actions. We validated the…
Retrieval finds a small number of relevant candidates from a large corpus for information retrieval and recommendation applications. A key component of retrieval is to model (user, item) similarity, which is commonly represented as the dot…
Human attention is a scarce resource in modern computing. A multitude of microtasks vie for user attention to crowdsource information, perform momentary assessments, personalize services, and execute actions with a single touch. A lot gets…
We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…
As online video content rapidly grows, the task of text-video retrieval (TVR) becomes increasingly important. A key challenge in TVR is the information asymmetry between video and text: videos are inherently richer in information, while…
Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are selected. Existing online selection strategies predominantly…
A movie's key moments stand out of the screenplay to grab an audience's attention and make movie browsing efficient. But a lack of annotations makes the existing approaches not applicable to movie key moment detection. To get rid of human…
Now that everyone can easily record videos, the quantity of which is continuously increasing, research on methods for improved video retrieval is important in the contemporary world. In cases where target videos are to be identified within…
Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a single matching moment for each query. This assumption does not always hold in real-world…
This paper presents a novel retrieval pipeline for video collections, which aims to retrieve the most significant parts of an edited video for a given query, and represent them with thumbnails which are at the same time semantically…