相关论文: BoxTuning: Directly Injecting the Object Box for M…
Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures…
Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…
To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The "Bounding Boxes in Text Transformer" (B2T2) also leverages referential information…
While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…
Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we explore the spatial…
Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of…
Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis…
Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…
With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications.…
Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…
Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs,…
Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…
Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer…
Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…
Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…
The field of object detection and understanding is rapidly evolving, driven by advances in both traditional CNN-based models and emerging multi-modal large language models (LLMs). While CNNs like ResNet and YOLO remain highly effective for…
In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…
Spatio-temporal video grounding (STVG) aims at localizing the spatio-temporal tube of a video, as specified by the input text query. In this paper, we utilize multimodal large language models (MLLMs) to explore a zero-shot solution in STVG.…
Recent advancements in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing diverse data types, yet significant disparities persist between human cognitive processes and computational approaches…
Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the large number of visual tokens. We propose KiToke, a training-free, query-agnostic token…