Related papers: Vote2Cap-DETR++: Decoupling Localization and Descr…
Benefiting from large-scale vision-language pre-training on image-text pairs, open-world detection methods have shown superior generalization ability under the zero-shot or few-shot detection settings. However, a pre-defined category space…
The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…
Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes a segment for each…
Localizing objects in 3D scenes according to the semantics of a given natural language is a fundamental yet important task in the field of multimedia understanding, which benefits various real-world applications such as robotics and…
Dense video captioning is an extremely challenging task since accurate and coherent description of events in a video requires holistic understanding of video contents as well as contextual reasoning of individual events. Most existing…
Inspired by recent advances in leveraging multiple modalities in machine translation, we introduce an encoder-decoder pipeline that uses (1) specific objects within an image and their object labels, (2) a language model for decoding joint…
Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervised detection (WSOD) methods relax the need for boxes to that…
Dense video captioning is a newly emerging task that aims at both localizing and describing all events in a video. We identify and tackle two challenges on this task, namely, (1) how to utilize both past and future contexts for accurate…
Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame…
Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…
Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods…
Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract…
Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…
3D shape captioning is a challenging application in 3D shape understanding. Captions from recent multi-view based methods reveal that they cannot capture part-level characteristics of 3D shapes. This leads to a lack of detailed part-level…
Image captioning is the process of automatically generating a description of an image in natural language. Image captioning is one of the significant challenges in image understanding since it requires not only recognizing salient objects…
This paper introduces our solution for Track 2 in AI City Challenge 2024. The task aims to solve traffic safety description and analysis with the dataset of Woven Traffic Safety (WTS), a real-world Pedestrian-Centric Traffic Video Dataset…
Previous studies on event camera sensing have demonstrated certain detection performance using dense event representations. However, the accumulated noise in such dense representations has received insufficient attention, which degrades the…
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a…
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their…
Deep learning exploits large volumes of labeled data to learn powerful models. When the target dataset is small, it is a common practice to perform transfer learning using pre-trained models to learn new task specific representations.…