Related papers: SpotEM: Efficient Video Search for Episodic Memory
Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…
Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untrimmed video is overlong, almost all existing VMR methods first sparsely down-sample each…
Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first…
Episodic memory retrieval enables wearable cameras to recall objects or events previously observed in video. However, existing formulations assume an "offline" setting with full video access at query time, limiting their applicability in…
We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human…
Precise Event Spotting (PES) aims to identify events and their class from long, untrimmed videos, particularly in sports. The main objective of PES is to detect the event at the exact moment it occurs. Existing methods mainly rely on…
Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…
Establishing object-level correspondence between egocentric and exocentric views is essential for intelligent assistants to deliver precise and intuitive visual guidance. However, this task faces numerous challenges, including extreme…
Humans share a strong tendency to memorize/forget some of the visual information they encounter. This paper focuses on providing computational models for the prediction of the intrinsic memorability of visual content. To address this new…
Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of continuous visual experience. In ultra-long video settings, relevant information is…
Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the…
Precise Event Spotting aims to localize fast-paced actions or events in videos with high temporal precision, a key task for applications in sports analytics, robotics, and autonomous systems. Existing methods typically process all frames…
Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is…
Using offline training schemes, researchers have tackled the event segmentation problem by providing full or weak-supervision through manually annotated labels or self-supervised epoch-based training. Most works consider videos that are at…
In this report, we present our champion solutions for the three egocentric video localization tracks of the Ego4D Episodic Memory Challenge at CVPR 2025. All tracks require precise localization of the interval within an untrimmed egocentric…
Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated…
In this technical report, we present our solution for the EgoPlan Challenge in ICML 2024. To address the real-world egocentric task planning problem, we introduce a novel planning framework which comprises three stages: long-term memory…
Vision-Language Models (VLMs) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by VLMs. Also, it is important to design tools that enable…
With the recent advances in video and 3D understanding, novel 4D spatio-temporal methods fusing both concepts have emerged. Towards this direction, the Ego4D Episodic Memory Benchmark proposed a task for Visual Queries with 3D Localization…
Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and…