Related papers: StructAlign: Structured Cross-Modal Alignment for …
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…
Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…
Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and…
Understanding neural responses to visual stimuli remains challenging due to the inherent complexity of brain representations and the modality gap between neural data and visual inputs. Existing methods, mainly based on reducing neural…
The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works learn to navigate step-by-step following an instruction. However, these works may fail to…
Multi-view clustering thrives in applications where views are collected in advance by extracting consistent and complementary information among views. However, it overlooks scenarios where data views are collected sequentially, i.e.,…
Human visual reconstruction aims to reconstruct fine-grained visual stimuli based on subject-provided descriptions and corresponding neural signals. As a widely adopted modality, Electroencephalography (EEG) captures rich visual cognition…
Federated learning enables multiple hospitals to cooperatively learn a shared model without privacy disclosure. Existing methods often take a common assumption that the data from different hospitals have the same modalities. However, such a…
Existing Vision Language Models (VLMs) often struggle to preserve logic, entity identity, and artistic style during extended, interleaved image-text interactions. We identify this limitation as "Multimodal Context Drift", which stems from…
Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…
The "style trap" poses a significant challenge for Large Vision-Language Models (LVLMs), hindering robust semantic understanding across diverse visual styles, especially in in-context learning (ICL). Existing methods often fail to…
Catastrophic forgetting remains a critical challenge in continual learning for large language models (LLMs), where models struggle to retain performance on historical tasks when fine-tuning on new sequential data without access to past…
Sign language recognition (SLR) plays a vital role in facilitating communication for the hearing-impaired community. SLR is a weakly supervised task where entire videos are annotated with glosses, making it challenging to identify the…
Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input…
Table structure recognition (TSR) holds widespread practical importance by parsing tabular images into structured representations, yet encounters significant challenges when processing complex layouts involving merged or empty cells.…
Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…
Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…
Composed Video Retrieval (CVR) is a challenging video retrieval task that utilizes multi-modal queries, consisting of a reference video and modification text, to retrieve the desired target video. The core of this task lies in understanding…
Video retrieval (VR) involves retrieving the ground truth video from the video database given a text caption or vice-versa. The two important components of compositionality: objects & attributes and actions are joined using correct syntax…
Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each modality into a single…