Related papers: Hierarchical Memory for Long Video QA
Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…
Multi-modal large language models (MLLMs) have demonstrated considerable potential across various downstream tasks that require cross-domain knowledge. MLLMs capable of processing videos, known as Video-MLLMs, have attracted broad interest…
Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time-quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes…
In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in videos. The problem requires comprehensive multimodal…
To date, visual question answering (VQA) (i.e., image QA and video QA) is still a holy grail in vision and language understanding, especially for video QA. Compared with image QA that focuses primarily on understanding the associations…
In this paper, we focus on video-to-text summarization and investigate how to best utilize multimodal information for summarizing long inputs (e.g., an hour-long TV show) into long outputs (e.g., a multi-sentence summary). We extend…
Understanding the content of videos is one of the core techniques for developing various helpful applications in the real world, such as recognizing various human actions for surveillance systems or customer behavior analysis in an…
Video question answering (VideoQA) is challenging given its multimodal combination of visual understanding and natural language processing. While most existing approaches ignore the visual appearance-motion information at different temporal…
Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by…
Empowered by Large Language Models (LLMs), recent advancements in Video-based LLMs (VideoLLMs) have driven progress in various video understanding tasks. These models encode video representations through pooling or query aggregation over a…
Recent long-form video-language understanding benchmarks have driven progress in video large multimodal models (Video-LMMs). However, the scarcity of well-annotated long videos has left the training of hour-long Video-LMMs underexplored. To…
Identifying a short segment in a long video that semantically matches a text query is a challenging task that has important application potentials in language-based video search, browsing, and navigation. Typical retrieval systems respond…
The recent growth of web video sharing platforms has increased the demand for systems that can efficiently browse, retrieve and summarize video content. Query-aware multi-video summarization is a promising technique that caters to this…
This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS)…
In this paper, we propose a Hierarchical Learned Video Compression (HLVC) method with three hierarchical quality layers and a recurrent enhancement network. The frames in the first layer are compressed by an image compression method with…
Real-time understanding of long video streams remains challenging for multimodal large language models (VLMs) due to redundant frame processing and rapid forgetting of past context. Existing streaming systems rely on fixed-interval decoding…
While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame sampling and static textual reasoning, which are inefficient and…
Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing…
Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…
Capturing complex hierarchical human activities, from atomic actions (e.g., picking up one present, moving to the sofa, unwrapping the present) to contextual events (e.g., celebrating Christmas) is crucial for achieving high-performance…