Related papers: VTAgent: Agentic Keyframe Anchoring for Evidence-A…
Visual Question Answering (VQA) concerns providing answers to Natural Language questions about images. Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. Whereas the task is grounded in…
Recent advancements in Video Large Language Models (VideoLLMs) have enabled strong performance across diverse multimodal video tasks. To reduce the high computational cost of processing dense video frames, efficiency-oriented methods such…
Recent advancements in Large Video Language Models (LVLMs) have highlighted their potential for multi-modal understanding, yet evaluating their factual grounding in videos remains a critical unsolved challenge. To address this gap, we…
Visual Grounding (VG) in Visual Question Answering (VQA) systems describes how well a system manages to tie a question and its answer to relevant image regions. Systems with strong VG are considered intuitively interpretable and suggest an…
Video-Question-Answering (VideoQA) comprises the capturing of complex visual relation changes over time, remaining a challenge even for advanced Video Language Models (VLM), i.a., because of the need to represent the visual content to a…
We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory…
Video Question Answering (VideoQA) requires identifying sparse critical moments in long videos and reasoning about their causal relationships to answer semantically complex questions. While recent advances in multimodal learning have…
Visual question answering (VQA) has been gaining a lot of traction in the machine learning community in the recent years due to the challenges posed in understanding information coming from multiple modalities (i.e., images, language). In…
The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are…
Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle…
Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is…
Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to…
Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets,…
Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a…
Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…
We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term…
Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs…
Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…
Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely…
Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process videos largely in a single-pass manner with limited support…